© 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. 10-GEMMASCOPE-RES-131K
    7. 104951
    Prev
    Next
    INDEX
    Explanations

    else or otherwise returning default

    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_10/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
     of
    -2.56
    //
    -1.98
     Not
    -1.54
     с
    -1.49
     zudem
    -1.48
    ꜄
    -1.45
    まさか
    -1.45
    /**
    -1.44
    不仅
    -1.44
    垕
    -1.41
    POSITIVE LOGITS
    鹚
    1.91
    ℣
    1.89
    殽
    1.79
    媜
    1.74
    𓆏
    1.73
    。
    1.69
     الأخرى
    1.68
    “
    1.66
    彞
    1.66
     presentará
    1.63
    Activations Density 0.002%

    No Known Activations