© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40194
    Prev
    Next
    INDEX
    Explanations

    relativistic case, therapy, aerobic, systems, omerty, spherical vesicles, beer, catecholamines, halogen light

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific or technical terms in academic/research papers, particularly in physics, chemistry, and medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to unusually long, multi-syllabic content words (especially technical or specialized terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Flug
    -0.98
    gasse
    -0.93
     voyageurs
    -0.93
    洒落
    -0.90
     their
    -0.87
    PATIENT
    -0.86
     myn
    -0.85
    响起
    -0.85
     finer
    -0.84
     fone
    -0.84
    POSITIVE LOGITS
     conventional
    0.94
     convencional
    0.90
     selección
    0.84
     ขาว
    0.83
     )}$
    0.82
    依然
    0.82
     класси
    0.82
    看到
    0.82
     Pueden
    0.82
    本地
    0.81
    Activations Density 0.148%

    No Known Activations