© 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. 129609
    Prev
    Next
    INDEX
    Explanations

    clearing out or raiding

    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
    (
    -1.65
    2
    -1.61
     gritty
    -1.48
    “
    -1.48
    <b>
    -1.43
    [
    -1.41
    роваться
    -1.39
     or
    -1.38
     uncles
    -1.34
     многие
    -1.32
    POSITIVE LOGITS
     tenues
    1.51
     cacher
    1.47
     maje
    1.40
    铪
    1.40
     fré
    1.38
     welkom
    1.38
     LIABLE
    1.37
     boute
    1.37
    を読んで
    1.36
    PRISE
    1.34
    Activations Density 0.020%

    No Known Activations