© 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. 71840
    Prev
    Next
    INDEX
    Explanations

    search, match, or GPT

    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
    ˒
    0.47
    ক
    0.47
    נן
    0.47
    เล่น
    0.45
    W
    0.44
     obtiene
    0.43
    Сегодня
    0.43
    ᄏ
    0.43
     Alegre
    0.43
    Ա
    0.43
    POSITIVE LOGITS
     zipped
    0.50
    火力
    0.48
    يدية
    0.46
     body
    0.44
     tubuh
    0.44
     ibu
    0.42
     BMI
    0.42
    衣服
    0.42
    ིན་
    0.41
     utilizzo
    0.41
    Activations Density 0.005%

    No Known Activations