© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32918
    Prev
    Next
    INDEX
    Explanations

    Ulaanbaatar, JSON, Disco Elysium

    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_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
     +
    0.49
     uppercase
    0.46
     We
    0.44
     Life
    0.43
     superscript
    0.43
     上
    0.42
     "+"
    0.42
     ionic
    0.42
     Pierre
    0.42
     ().
    0.42
    POSITIVE LOGITS
    áni
    0.54
     रोकता
    0.54
    ат
    0.51
     likewise
    0.51
    ᄒ
    0.50
     therefor
    0.49
    ेर
    0.48
    fNil
    0.48
    ла
    0.47
     inició
    0.47
    Activations Density 0.000%

    No Known Activations