© 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-65K
    7. 13568
    Prev
    Next
    INDEX
    Explanations

    Target specific context

    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_65k_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
     кілька
    0.44
    него
    0.43
    ிகள்
    0.41
    生産
    0.38
    ඥ
    0.38
     dhe
    0.37
     інші
    0.37
     صلى
    0.37
     ისინი
    0.37
    optim
    0.36
    POSITIVE LOGITS
    مكان
    0.49
    on
    0.49
    ل
    0.46
    ົ
    0.43
    ون
    0.41
    Hend
    0.41
    S
    0.41
     recorr
    0.40
    K
    0.40
    ाब
    0.40
    Activations Density 0.002%

    No Known Activations