© 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. 123701
    Prev
    Next
    INDEX
    Explanations

    non-infringement, non-guaranteeing

    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
    袭击
    0.46
     qualche
    0.45
    辈子
    0.45
     ሁለት
    0.44
     nějak
    0.43
    谟
    0.43
    麃
    0.43
     decisão
    0.43
     నాగ
    0.43
     opción
    0.43
    POSITIVE LOGITS
    as
    0.56
    in
    0.53
     and
    0.50
    and
    0.47
    ih
    0.47
    kan
    0.45
    w
    0.44
     K
    0.42
    ≤
    0.42
    ism
    0.42
    Activations Density 0.004%

    No Known Activations