© 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. 22-GEMMASCOPE-RES-131K
    7. 67485
    Prev
    Next
    INDEX
    Explanations

    Professional services or specific terms

    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_22/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
    借助
    -1.03
    Eleven
    -0.92
    Snackbar
    -0.90
    ByteBuf
    -0.89
     свої
    -0.88
    ¯
    -0.87
    失去
    -0.86
    ुनिया
    -0.85
    utveck
    -0.85
    gnings
    -0.85
    POSITIVE LOGITS
     from
    0.85
     CALIFORN
    0.84
    𖤣
    0.84
    Nokia
    0.84
    profess
    0.83
     preguntó
    0.82
     görd
    0.81
    Leve
    0.81
     créateur
    0.81
     assigned
    0.80
    Activations Density 0.067%

    No Known Activations