© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168975
    Prev
    Next
    INDEX
    Explanations

    accessing variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    と思いますが
    0.47
    ขา
    0.44
    indeterminate
    0.43
    COLUMN
    0.42
     žiad
    0.42
    ู
    0.42
    li
    0.41
     approved
    0.41
    ט
    0.40
    Berg
    0.40
    POSITIVE LOGITS
     emisiones
    0.47
     preparada
    0.45
     produ
    0.45
    तेल
    0.44
     例如
    0.44
     produzido
    0.43
     ejemplos
    0.42
     Некоторые
    0.42
     lograr
    0.42
     telefono
    0.41
    Activations Density 0.006%

    No Known Activations