© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12292
    Prev
    Next
    INDEX
    Explanations

    content and database access

    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
     people
    -1.41
     but
    -1.30
    يده
    -1.28
    alertDialog
    -1.27
     Instagram
    -1.20
    contented
    -1.20
    亙
    -1.18
    饌
    -1.16
     team
    -1.13
    ;#
    -1.13
    POSITIVE LOGITS
     APPELL
    1.51
    וּ
    1.41
     traité
    1.36
    וֹ
    1.23
    ־ה
    1.20
    onomies
    1.20
     PLAINT
    1.18
     relâche
    1.18
     CONDUIT
    1.17
     Оте
    1.17
    Activations Density 0.039%

    No Known Activations