© 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. 112540
    Prev
    Next
    INDEX
    Explanations

    Brennan, MH, Guatemala, seroconversion

    np_acts-logits-general · gemini-2.5-flash-lite

    names that include "Brennan" and medical abbreviations starting with "MH".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ropractor
    -2.58
    pecabe
    -2.58
     ciertas
    -2.48
     vorigen
    -2.45
    ()){
    -2.44
    中年
    -2.41
     Ganzen
    -2.38
    耽
    -2.34
    眼睛
    -2.31
    óis
    -2.31
    POSITIVE LOGITS
    U
    3.08
    a
    2.95
    '
    2.89
    余談
    2.73
    昻
    2.69
    になりますが
    2.67
    なんとなく
    2.67
    B
    2.58
    ～　
    2.45
    ねぇ
    2.42
    Activations Density 0.005%

    No Known Activations