© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106850
    Prev
    Next
    INDEX
    Explanations

    diet, shares, rows affected

    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
    $\
    -1.25
    ABI
    -0.81
     $\
    -0.75
    ulity
    -0.74
    EFIAPI
    -0.71
    $^{
    -0.69
     {$\
    -0.67
    -0.67
     mỡ
    -0.67
     双
    -0.65
    POSITIVE LOGITS
    鴦
    0.90
    失礼
    0.78
     strict
    0.73
    sourced
    0.73
     initWithFrame
    0.73
    杳
    0.73
    nait
    0.73
    filepath
    0.73
    partic
    0.73
    qli
    0.72
    Activations Density 0.001%
    No Known Activations