© 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. 22-GEMMASCOPE-RES-131K
    7. 27035
    Prev
    Next
    INDEX
    Explanations

    branch height and width

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

    The main thing this neuron does is pick out specialized scientific or technical jargon—particularly domain-specific nouns like measurement/instrumentation terms, disease names, and reference/citation IDs.

    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
     nachts
    -0.98
     पढ़
    -0.96
     bezpiecz
    -0.95
     Vorbild
    -0.94
     Entsche
    -0.94
     verschiedener
    -0.92
     Wählen
    -0.91
    ਫ਼
    -0.90
     Funktionalität
    -0.90
    再來
    -0.90
    POSITIVE LOGITS
     and
    1.15
    acağına
    1.09
    couvrir
    0.96
     SICK
    0.91
     to
    0.91
     игрушка
    0.91
    หรือ
    0.90
    aconda
    0.89
     Mannes
    0.88
     —
    0.87
    Activations Density 0.104%

    No Known Activations