© 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. 45309
    Prev
    Next
    INDEX
    Explanations

    product designs and attributes

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

    introduction and context setting

    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
     skall
    0.80
    젼
    0.80
     insures
    0.75
     insure
    0.72
     라고
    0.67
     까지
    0.66
     কারন
    0.63
     accomod
    0.62
     আশংকা
    0.61
     उन्ह
    0.61
    POSITIVE LOGITS
    🫶
    0.92
     TikTok
    0.89
    TikTok
    0.89
    🫢
    0.88
     проє
    0.84
     Metaverse
    0.84
     YouTuber
    0.81
    IoT
    0.80
     metaverse
    0.80
     ২০২২
    0.80
    Activations Density 0.093%

    No Known Activations