© 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. 107112
    Prev
    Next
    INDEX
    Explanations

    Children's institutions and organizations

    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
    カーテン
    -0.82
    surveys
    -0.82
     aner
    -0.82
     étanche
    -0.78
     élève
    -0.76
     sonnen
    -0.76
    条件
    -0.75
    瘋
    -0.75
    Surveys
    -0.75
     Spreading
    -0.75
    POSITIVE LOGITS
     television
    0.88
     Liturgy
    0.82
     Crusade
    0.82
     Hospital
    0.82
    album
    0.81
    EFF
    0.80
     Hour
    0.79
    頤
    0.79
    Hrs
    0.79
     Zen
    0.79
    Activations Density 0.022%

    No Known Activations