© 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. 48929
    Prev
    Next
    INDEX
    Explanations

    foreign languages mixed with English

    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
    畯
    0.51
    ד
    0.48
     immunost
    0.47
     사용하여
    0.46
     scrot
    0.44
    Periph
    0.44
     testicule
    0.43
     semanal
    0.43
    ཥ
    0.43
     convexo
    0.42
    POSITIVE LOGITS
    in
    0.50
     bukanlah
    0.48
     history
    0.46
     relatable
    0.45
     In
    0.44
     remind
    0.44
     President
    0.44
    history
    0.44
     পারেনি
    0.42
     مليار
    0.42
    Activations Density 0.030%

    No Known Activations