© 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. 87279
    Prev
    Next
    INDEX
    Explanations

    crafting and improving

    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
    鬭
    -1.70
    🤮
    -1.66
    🤯
    -1.66
    🤨
    -1.64
    vaila
    -1.62
    😄
    -1.60
    🤢
    -1.59
    🥴
    -1.59
     👎
    -1.56
    ☺
    -1.55
    POSITIVE LOGITS
     a
    1.79
    <
    1.65
     Four
    1.59
     for
    1.54
     not
    1.52
     other
    1.44
     Five
    1.42
     Three
    1.41
     Nine
    1.41
     —
    1.39
    Activations Density 0.014%

    No Known Activations