© 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. 2981
    Prev
    Next
    INDEX
    Explanations

    direction and movement

    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
    ؟!
    0.37
    সংযোগ
    0.37
    س
    0.37
    👼
    0.36
     })
    0.36
     ওকে
    0.36
     ഒഴിവാ
    0.36
     মস্তি
    0.35
    ?”,
    0.35
    V
    0.34
    POSITIVE LOGITS
     from
    0.46
     of
    0.46
     for
    0.44
     with
    0.42
     in
    0.41
    ρι
    0.39
    ри
    0.39
     on
    0.38
    ла
    0.38
     out
    0.38
    Activations Density 0.137%

    No Known Activations