© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84453
    Prev
    Next
    INDEX
    Explanations

    Southeastern Ohio, South East Asia, SEHK

    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
    厕
    -0.88
    Slap
    -0.83
    insegna
    -0.83
     lebens
    -0.82
     kept
    -0.81
    を開始
    -0.79
     strengthened
    -0.79
     esfuer
    -0.79
    nila
    -0.79
     dần
    -0.78
    POSITIVE LOGITS
     Se
    1.15
     SE
    0.99
     Се
    0.96
    Se
    0.92
    ised
    0.88
    ested
    0.87
    ither
    0.86
    Мекси
    0.81
    endosi
    0.81
    ValueStyle
    0.80
    Activations Density 0.073%

    No Known Activations