© 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. 12384
    Prev
    Next
    INDEX
    Explanations

    code snippet formatting

    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
     السياس
    -1.30
     until
    -1.26
     Preferencias
    -1.20
     derer
    -1.19
     ZDF
    -1.19
    Приятного
    -1.16
    kadın
    -1.09
    ;%%
    -1.09
     muualla
    -1.09
    箓
    -1.08
    POSITIVE LOGITS
     frequentemente
    1.23
     possible
    1.22
     الشاشة
    1.20
    viedo
    1.16
     repertoire
    1.13
     ouvido
    1.13
     سيكون
    1.12
     pertinente
    1.12
    сед
    1.11
     obligatorio
    1.09
    Activations Density 0.000%

    No Known Activations