© 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. 22-GEMMASCOPE-RES-131K
    7. 65142
    Prev
    Next
    INDEX
    Explanations

    product descriptions

    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
     моего
    -1.50
     Obwohl
    -1.48
     my
    -1.35
     sezonu
    -1.34
     Ähnliche
    -1.28
     Danach
    -1.27
     klienta
    -1.27
     mojej
    -1.27
     naszych
    -1.24
     açıklama
    -1.23
    POSITIVE LOGITS
     your
    2.08
     you
    1.95
    ḏ
    1.38
    ďaka
    1.24
     JULY
    1.23
     vous
    1.14
     youre
    1.13
     Ihrem
    1.13
     paulo
    1.13
    ṯ
    1.11
    Activations Density 0.044%

    No Known Activations