© 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. 12336
    Prev
    Next
    INDEX
    Explanations

    path components

    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
     ktoś
    -1.15
    $,
    -1.08
     sessão
    -1.05
     câmera
    -1.02
    pantalon
    -1.00
     سپس
    -0.99
    хол
    -0.98
    xiety
    -0.97
    君は
    -0.96
     Japão
    -0.96
    POSITIVE LOGITS
    توضیحات
    1.23
    ̍t
    1.20
    معرفی
    1.16
    however
    1.15
    萦
    1.13
    cedent
    1.11
     пад
    1.10
    汹
    1.09
    vaders
    1.09
    ⒋
    1.05
    Activations Density 0.001%

    No Known Activations