© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15438
    Prev
    Next
    INDEX
    Explanations

    一, 二, 三

    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
    in
    -4.03
     namun
    -2.72
     these
    -2.70
    to
    -2.67
     tetapi
    -2.66
     when
    -2.63
     companies
    -2.52
    am
    -2.48
     both
    -2.44
     theres
    -2.44
    POSITIVE LOGITS
    
    2.69
    彞
    2.55
    狲
    2.50
    梘
    2.50
    ครื่อง
    2.50
     ſie
    2.45
    YNAMIC
    2.36
    珦
    2.34
    The
    2.33
     poë
    2.33
    Activations Density 0.001%

    No Known Activations