© 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. 130649
    Prev
    Next
    INDEX
    Explanations

    bits of information

    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
     giacca
    -1.60
     męska
    -1.58
    我们
    -1.54
    悒
    -1.54
    jų
    -1.53
    𓍯
    -1.51
     parete
    -1.47
     caros
    -1.45
     оценка
    -1.45
    噥
    -1.45
    POSITIVE LOGITS
     Erfindung
    1.88
    !"
    1.62
     $
    1.61
    mandu
    1.58
    erráneo
    1.55
    «
    1.54
     «
    1.52
     στην
    1.51
     I
    1.49
     possono
    1.49
    Activations Density 0.033%

    No Known Activations