© 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. 30092
    Prev
    Next
    INDEX
    Explanations

    audio player, video browser

    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
    ຈາກ
    0.43
    Effective
    0.42
    辮
    0.40
     Effective
    0.40
    ިޔ
    0.40
    יות
    0.40
    adder
    0.39
    RELATED
    0.39
    ETON
    0.39
     tématu
    0.39
    POSITIVE LOGITS
     depl
    0.46
     peregr
    0.44
     conducts
    0.42
    诟
    0.40
     loaded
    0.39
     gange
    0.39
     rolls
    0.38
    뚱
    0.38
     secondaires
    0.37
     schade
    0.37
    Activations Density 0.001%

    No Known Activations