© 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. 22-GEMMASCOPE-RES-131K
    7. 129906
    Prev
    Next
    INDEX
    Explanations

    SELECT FROM sys.columns;

    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_22/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
     indien
    -1.19
     to
    -1.12
     några
    -1.06
    ȏ
    -1.02
     overloaded
    -1.02
    個人的には
    -0.99
    blox
    -0.99
    nese
    -0.97
    IDAS
    -0.97
    ならば
    -0.97
    POSITIVE LOGITS
     things
    1.16
    自从
    1.13
     them
    1.13
    んですよ
    1.11
    ését
    1.05
    なのでしょう
    1.03
    <!--
    1.01
     ചെയ
    1.01
    things
    1.00
    小時
    0.99
    Activations Density 0.012%

    No Known Activations