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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13143
    Prev
    Next
    INDEX
    Explanations

    CRE AT

    np_acts-logits-general · gemini-2.5-flash-lite

    afternoon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ه‌
    0.33
     আদালত
    0.32
    َل
    0.31
     marquées
    0.30
    禧
    0.30
    代谢
    0.30
    σετε
    0.29
    َن
    0.29
    ότητας
    0.29
     হাস্য
    0.29
    POSITIVE LOGITS
    the
    0.35
    text
    0.34
    to
    0.32
    align
    0.31
    In
    0.30
     In
    0.30
    many
    0.30
    long
    0.29
    boost
    0.29
    multi
    0.29
    Activations Density 0.002%

    No Known Activations