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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7567
    Prev
    Next
    INDEX
    Explanations

    beginning of lists, sequences, or tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    s
    2.28
    ς
    2.26
    ャ
    1.82
     coinc
    1.79
     Unpublished
    1.75
     appré
    1.70
     cohesion
    1.66
    Este
    1.65
     Einrichtung
    1.65
    জা
    1.64
    POSITIVE LOGITS
    至於
    1.78
     следует
    1.76
    enment
    1.67
    𝔂
    1.59
    飧
    1.58
    enang
    1.57
    \!\
    1.55
    alcoholic
    1.55
    o
    1.55
    𝓮
    1.52
    Activations Density 0.000%

    No Known Activations