© 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. 14015
    Prev
    Next
    INDEX
    Explanations

    pairs followed by are

    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
     
    0.46
    ↵
    0.43
     visibly
    0.42
     impressive
    0.41
     resistance
    0.41
    G
    0.41
    он
    0.40
     resistances
    0.40
     piles
    0.39
     culture
    0.39
    POSITIVE LOGITS
    墅
    0.46
     अथवा
    0.44
    Населення
    0.42
     बरेली
    0.41
     Änder
    0.40
     അവര്‍
    0.40
    发展的
    0.40
    viä
    0.40
     následuj
    0.40
    casters
    0.39
    Activations Density 0.000%

    No Known Activations