© 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. 69363
    Prev
    Next
    INDEX
    Explanations

    keywords followed by punctuation or descriptions

    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
    癀
    -2.02
     muitos
    -1.77
     hiçbir
    -1.73
    𖣘
    -1.66
     the
    -1.66
     aimé
    -1.65
     wspania
    -1.63
    𐐀
    -1.63
    岀
    -1.59
     furiously
    -1.57
    POSITIVE LOGITS
    What
    2.19
    Perhaps
    2.08
    Surprisingly
    2.06
    They
    1.96
    However
    1.93
    2
    1.90
    Typically
    1.84
    Although
    1.84
    Probably
    1.82
    Following
    1.81
    Activations Density 0.002%

    No Known Activations