© 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. 92775
    Prev
    Next
    INDEX
    Explanations

    trust beneficiaries

    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
    newtheorem
    -0.97
    MERGE
    -0.84
    īts
    -0.77
     Ō
    -0.77
    žiaga
    -0.77
    海鲜
    -0.76
    kee
    -0.75
     memperhatikan
    -0.75
     jornada
    -0.75
     Tyres
    -0.75
    POSITIVE LOGITS
    umur
    0.83
    เคล
    0.82
     Lasting
    0.81
    诵
    0.75
     Will
    0.73
     mirrors
    0.73
    Executors
    0.72
     ウィ
    0.71
     execu
    0.70
     abroad
    0.69
    Activations Density 0.012%

    No Known Activations