Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 99075
    Prev
    Next
    INDEX
    Explanations

    list items and descriptions

    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_40_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
    ктором
    0.39
    晛
    0.39
     captivated
    0.38
    Park
    0.38
    Manisha
    0.37
    Parameteri
    0.37
     mãn
    0.36
    췌
    0.36
    秒
    0.35
     जिला
    0.35
    POSITIVE LOGITS
     продол
    0.44
     um
    0.43
    consistency
    0.41
     stark
    0.40
     lack
    0.39
     subst
    0.39
    也可
    0.39
     टेली
    0.39
     Uz
    0.37
     Lidl
    0.37
    Activations Density 0.000%

    No Known Activations