© 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. 57440
    Prev
    Next
    INDEX
    Explanations

    Muller, Busch, Brazil, Khan, Park

    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
    dopodob
    -0.84
    lový
    -0.81
     Hause
    -0.81
     боле
    -0.81
     ingin
    -0.78
    ステン
    -0.74
    /");
    -0.73
    ❜
    -0.73
    cuado
    -0.72
    ława
    -0.72
    POSITIVE LOGITS
     hardness
    0.77
    Portion
    0.76
     APO
    0.75
    できません
    0.75
     Portion
    0.75
    חו
    0.72
    気で
    0.71
    heder
    0.71
    一条
    0.71
     Veget
    0.70
    Activations Density 0.041%

    No Known Activations