© 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. 84063
    Prev
    Next
    INDEX
    Explanations

    gotta followed by a verb

    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
    g
    -3.03
    b
    -2.89
    e
    -2.70
    h
    -2.55
    il
    -2.48
    es
    -2.48
     meisten
    -2.42
    w
    -2.36
    on
    -2.25
    i
    -2.25
    POSITIVE LOGITS
     become
    3.00
    寕
    2.31
    𖣘
    2.31
    鵟
    2.30
    鯷
    2.27
     sorta
    2.22
    轳
    2.17
     préféré
    2.16
    Only
    2.16
    .
    2.14
    Activations Density 0.000%

    No Known Activations