© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78209
    Prev
    Next
    INDEX
    Explanations

    At followed by time or event

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

    at its core, foundation

    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
    賭
    0.48
    瞬间
    0.47
     смотре
    0.46
     चाह
    0.45
     순간
    0.44
     desperate
    0.44
     കിട
    0.44
    澆
    0.43
    ুবাদ
    0.42
    恐怖
    0.42
    POSITIVE LOGITS
     requested
    0.52
     request
    0.47
    &$
    0.46
     Share
    0.46
     &
    0.45
     presented
    0.44
    orn
    0.43
     requests
    0.43
     announced
    0.43
     A
    0.42
    Activations Density 0.024%

    No Known Activations