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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109060
    Prev
    Next
    INDEX
    Explanations

    questions asked with Q:

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

    The neuron fires on standalone header or label tokens—words you’d find in section titles, document headings, or config‐style identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     különböző
    -1.06
     gyere
    -1.03
     cikk
    -0.95
     např
    -0.94
     موبایل
    -0.90
     tegens
    -0.88
     milyen
    -0.85
     др
    -0.85
     yapımı
    -0.82
    嗮
    -0.82
    POSITIVE LOGITS
     tonight
    0.93
    argc
    0.92
     giants
    0.85
     very
    0.84
     maniera
    0.82
    olar
    0.81
    Matéri
    0.81
     hopeful
    0.81
    UserID
    0.81
     computa
    0.80
    Activations Density 0.000%

    No Known Activations