© 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. 28382
    Prev
    Next
    INDEX
    Explanations

    photograph portrait imagery prevent funny

    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
    ซื้อ
    0.54
     dimensioni
    0.52
    Kan
    0.47
    ออกแบบ
    0.47
    ن
    0.47
    内容
    0.47
     Kan
    0.46
     maximized
    0.46
    に参加
    0.45
    ش
    0.45
    POSITIVE LOGITS
    гает
    0.51
    ALP
    0.46
    mation
    0.46
    stressed
    0.45
    })+\
    0.44
    ॉट
    0.42
    uty
    0.42
     Ці
    0.41
     estrés
    0.41
    multirow
    0.40
    Activations Density 0.001%

    No Known Activations