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. 2248
    Prev
    Next
    INDEX
    Explanations

    text following bolded section

    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
     privind
    0.20
     щодо
    0.17
    ϓ
    0.16
    ექტ
    0.16
     für
    0.15
     ከ
    0.15
    ेटेड
    0.15
     দুদকের
    0.15
    PG
    0.15
     Př
    0.15
    POSITIVE LOGITS
     mesela
    0.17
    attamente
    0.17
    ....
    0.16
    <blockquote>
    0.16
     somehow
    0.16
    ляться
    0.16
    ….
    0.16
    atthena
    0.16
     একটা
    0.16
    やら
    0.16
    Activations Density 1.512%

    No Known Activations