© 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. 125439
    Prev
    Next
    INDEX
    Explanations

    part of a larger sequence

    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
    Sub
    0.50
    Dict
    0.48
    Succ
    0.47
    دا
    0.44
    兹
    0.44
     and
    0.44
     د
    0.41
     ر
    0.41
    Aire
    0.41
     و
    0.40
    POSITIVE LOGITS
     Translated
    0.47
     interdependent
    0.45
     instit
    0.45
     timeouts
    0.45
     kontak
    0.45
     patitth
    0.43
     Wada
    0.43
    ());
    0.43
     pudd
    0.43
     interdependence
    0.43
    Activations Density 0.003%

    No Known Activations