© 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. 20222
    Prev
    Next
    INDEX
    Explanations

    no real-time information

    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
    ﾈ
    0.53
    ড
    0.49
    шка
    0.49
    Ev
    0.47
    يق
    0.47
    يب
    0.46
    Automatic
    0.46
    О
    0.46
    يت
    0.46
    Isn
    0.46
    POSITIVE LOGITS
    an
    0.59
     antif
    0.48
     대응
    0.47
     ders
    0.47
     scraped
    0.47
     an
    0.46
     pur
    0.45
     anti
    0.44
    pur
    0.44
     όπως
    0.43
    Activations Density 0.011%

    No Known Activations