© 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. 102509
    Prev
    Next
    INDEX
    Explanations

    dates and registration

    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
    ?
    -1.43
    >
    -1.20
     h
    -1.20
     doing
    -1.20
     people
    -1.16
     an
    -1.13
    ของ
    -1.11
     their
    -1.09
    D
    -1.09
     як
    -1.08
    POSITIVE LOGITS
    annique
    1.59
    Adapt
    1.38
     trasm
    1.30
     gerekli
    1.29
     rusa
    1.29
     posteriore
    1.27
     tradizionale
    1.26
     贝
    1.25
     Selamat
    1.25
    aktiv
    1.25
    Activations Density 0.628%

    No Known Activations