© 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. 31254
    Prev
    Next
    INDEX
    Explanations

    contact support or information

    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
     Tuchel
    -0.82
    bní
    -0.77
     Charter
    -0.72
    Charter
    -0.72
    TRAINING
    -0.71
     dysfunctional
    -0.70
     válto
    -0.70
     OEM
    -0.69
     Ilya
    -0.69
     cuerpo
    -0.69
    POSITIVE LOGITS
    游戏亮点
    0.73
     Res
    0.68
    ethylene
    0.66
    zygous
    0.65
    ustomed
    0.65
    jącego
    0.65
    intend
    0.64
    クッション
    0.64
     lettura
    0.64
    asia
    0.63
    Activations Density 0.032%

    No Known Activations