© 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. 66186
    Prev
    Next
    INDEX
    Explanations

    collide with

    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
    This
    -3.52
    You
    -3.16
    na
    -2.89
    We
    -2.75
    If
    -2.73
    As
    -2.69
    The
    -2.58
    h
    -2.58
    To
    -2.53
    de
    -2.45
    POSITIVE LOGITS
    极其
    2.55
    
    2.39
     caminh
    2.30
    風邪
    2.28
     dijeron
    2.28
    kunjung
    2.22
     personalidades
    2.19
    ᷇
    2.16
     ſou
    2.16
     ridurre
    2.16
    Activations Density 0.007%

    No Known Activations