© 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. 170039
    Prev
    Next
    INDEX
    Explanations

    movement restrictions

    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
    跇
    0.82
     :).
    0.79
     everytime
    0.79
     jeśli
    0.75
    เพราะ
    0.74
     davvero
    0.73
     dacă
    0.73
    ！！！
    0.73
    !।
    0.73
     براي
    0.73
    POSITIVE LOGITS
    ’
    0.86
     are
    0.79
    '
    0.78
    G
    0.70
    S
    0.68
    F
    0.68
     C
    0.68
    E
    0.67
    A
    0.66
     were
    0.65
    Activations Density 0.001%

    No Known Activations