© 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. 12725
    Prev
    Next
    INDEX
    Explanations

    find links to videos

    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
    MenuActive
    0.49
    ﺵ
    0.41
    レクト
    0.40
     surnames
    0.39
    ્વા
    0.39
    эн
    0.39
     prefix
    0.38
     suffix
    0.38
     пространство
    0.38
    DUC
    0.37
    POSITIVE LOGITS
     Mariah
    0.41
    只有
    0.40
     হয়ত
    0.40
     ma
    0.39
    
    0.38
    केज
    0.38
     Territorial
    0.38
    video
    0.37
    创意
    0.37
    тык
    0.37
    Activations Density 0.001%

    No Known Activations