© 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. 84044
    Prev
    Next
    INDEX
    Explanations

    about every, anything, any, each

    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
    )$
    -1.94
     mangled
    -1.89
    新た
    -1.88
    replyreport
    -1.86
    ჻
    -1.84
     docile
    -1.80
     geniuses
    -1.79
     է
    -1.79
    dersfield
    -1.77
    荦
    -1.74
    POSITIVE LOGITS
     variety
    2.02
     considered
    1.98
    t
    1.86
     also
    1.83
    This
    1.82
     uses
    1.80
     too
    1.80
    〟
    1.78
     already
    1.78
    What
    1.78
    Activations Density 0.003%

    No Known Activations