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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118853
    Prev
    Next
    INDEX
    Explanations

    age ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ArrayList
    -0.84
    lador
    -0.75
    ၃
    -0.73
     tertiary
    -0.72
     each
    -0.72
     الثالث
    -0.71
     ө
    -0.71
     условиях
    -0.71
    abancı
    -0.70
    lll
    -0.69
    POSITIVE LOGITS
    MouseEvent
    0.86
    unz
    0.77
    umir
    0.75
     angegeben
    0.74
    Ри
    0.72
     royals
    0.71
     qualités
    0.71
    arbeitet
    0.71
     Huffman
    0.71
     DMT
    0.70
    Activations Density 0.062%

    No Known Activations