© 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. 113468
    Prev
    Next
    INDEX
    Explanations

    social considerations and risks

    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
     ಸಮಯದಲ್ಲಿ
    0.51
    Vous
    0.50
     étapes
    0.50
    Lors
    0.49
    ਲ
    0.49
     attaques
    0.47
    const
    0.47
    i
    0.46
    ne
    0.45
    class
    0.45
    POSITIVE LOGITS
     sConfig
    0.47
     социа
    0.46
     Society
    0.46
     Corb
    0.46
     Historically
    0.46
     surve
    0.45
     Haskell
    0.45
     Latte
    0.45
     Sociedad
    0.44
     නිෂ්පා
    0.44
    Activations Density 0.001%

    No Known Activations