© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86093
    Prev
    Next
    INDEX
    Explanations

    flat things

    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
    ᨆ
    -2.61
    ᨈ
    -2.56
    人たち
    -2.55
     mesmas
    -2.52
     promove
    -2.52
     เรา
    -2.48
    ものに
    -2.47
    蚨
    -2.45
    書いた
    -2.45
     INFORMACIÓN
    -2.44
    POSITIVE LOGITS
    i
    3.27
    For
    2.91
    Other
    2.73
    To
    2.72
    出て
    2.67
    Only
    2.66
    All
    2.63
    3
    2.63
     reviewing
    2.63
    One
    2.58
    Activations Density 0.007%

    No Known Activations