© 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. 30301
    Prev
    Next
    INDEX
    Explanations

    didn't get

    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
     настолько
    0.47
     overruled
    0.42
    樾
    0.42
    Vere
    0.40
    并非
    0.40
    arze
    0.40
    离开了
    0.40
     વ્ય
    0.40
     విశ్వ
    0.40
     недостаточно
    0.40
    POSITIVE LOGITS
    '];?>
    0.46
     なかっ
    0.46
     splic
    0.45
    ER
    0.44
     sik
    0.43
     residual
    0.43
     eran
    0.43
     pieza
    0.42
     ocur
    0.42
     suelo
    0.42
    Activations Density 0.002%

    No Known Activations