© 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. 106623
    Prev
    Next
    INDEX
    Explanations

    without restriction

    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
    屬
    -0.69
    ặp
    -0.66
    uten
    -0.65
     polyg
    -0.65
    Model
    -0.65
    قال
    -0.63
    筋
    -0.63
    Species
    -0.63
     Settle
    -0.63
    Anonymous
    -0.63
    POSITIVE LOGITS
     couv
    0.72
     relatifs
    0.69
    InitialState
    0.69
    ренко
    0.67
     Hound
    0.66
     provi
    0.66
     adaptés
    0.66
     houver
    0.66
     communs
    0.66
    枪
    0.65
    Activations Density 0.112%

    No Known Activations