© 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. 143525
    Prev
    Next
    INDEX
    Explanations

    parenthetical explanations

    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
     صدر
    0.44
    inders
    0.43
     Religions
    0.43
     Calcium
    0.43
     sacred
    0.43
    𝘮
    0.43
     पवित्र
    0.42
     resins
    0.41
     நூற்றாண்ட
    0.41
    詆
    0.41
    POSITIVE LOGITS
     it
    0.50
     makes
    0.43
     gives
    0.42
     bringt
    0.42
    动
    0.42
     lifting
    0.41
     will
    0.41
     woo
    0.40
     giving
    0.40
    ляет
    0.40
    Activations Density 0.017%

    No Known Activations