© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27081
    Prev
    Next
    INDEX
    Explanations

    whimsical relationship to the word

    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
     effluents
    0.53
     sintered
    0.52
     gauze
    0.51
    子は
    0.51
     produits
    0.50
    幟
    0.50
     завода
    0.49
    maxage
    0.48
     products
    0.48
     ripening
    0.48
    POSITIVE LOGITS
     on
    0.52
    关
    0.50
    ك
    0.47
    ت
    0.47
    ק
    0.46
    ারের
    0.45
     Alas
    0.44
    مت
    0.42
    评论
    0.41
     imdb
    0.40
    Activations Density 0.000%

    No Known Activations