© 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. 128812
    Prev
    Next
    INDEX
    Explanations

    !important, !default, !global

    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
     by
    -2.34
     after
    -2.14
     while
    -2.03
     what
    -1.95
     and
    -1.88
     even
    -1.84
     one
    -1.84
    ”
    -1.80
    .”
    -1.80
     Although
    -1.80
    POSITIVE LOGITS
    튿
    2.03
    휀
    1.80
     amazingly
    1.79
    鹮
    1.79
     insanely
    1.71
     angene
    1.68
    UTED
    1.63
    ichtete
    1.63
     ſie
    1.63
     juiste
    1.62
    Activations Density 0.003%

    No Known Activations