© 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. 10-GEMMASCOPE-RES-131K
    7. 58749
    Prev
    Next
    INDEX
    Explanations

    later when

    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
    𖣔
    -2.95
    谖
    -2.52
     eerste
    -2.48
    踅
    -2.47
     planific
    -2.42
    氿
    -2.39
    ebab
    -2.38
    ݮ
    -2.36
     aloj
    -2.33
    𓇼
    -2.33
    POSITIVE LOGITS
    that
    3.47
     That
    3.27
    most
    3.13
    i
    3.02
    an
    2.98
    3
    2.92
    8
    2.77
    as
    2.69
     ataupun
    2.69
    Not
    2.66
    Activations Density 0.024%

    No Known Activations