© 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. 1131
    Prev
    Next
    INDEX
    Explanations

    Alexandria Eld Shelby

    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
    0
    -2.83
    the
    -2.77
    you
    -2.55
    8
    -2.53
    where
    -2.53
    es
    -2.52
    This
    -2.48
    ко
    -2.44
    What
    -2.44
     шесть
    -2.42
    POSITIVE LOGITS
    ﮯ
    2.89
    新能源
    2.59
    ではない
    2.53
    䊊
    2.52
    ࿙
    2.52
     italien
    2.33
    珵
    2.33
    ⡦
    2.30
    стреча
    2.30
     auch
    2.30
    Activations Density 0.010%

    No Known Activations