© 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. 69801
    Prev
    Next
    INDEX
    Explanations

    people's names and titles

    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
    новь
    -1.30
    Спољашње
    -1.26
     costuras
    -1.20
     clunky
    -1.20
    }));
    -1.19
    ähän
    -1.18
    ϱ
    -1.18
    ousine
    -1.18
     Wartawan
    -1.16
    町村
    -1.16
    POSITIVE LOGITS
     on
    1.20
     Tatsache
    1.20
    einem
    1.17
    زاری
    1.16
     still
    1.12
     Nachteile
    1.12
    去做
    1.10
     possível
    1.09
     Hände
    1.09
     they
    1.09
    Activations Density 0.009%

    No Known Activations