© 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. 207309
    Prev
    Next
    INDEX
    Explanations

    track, striking, the, only, for, indicates

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

    potential for growth

    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
    Negative Logits
    嶂
    0.49
     автора
    0.48
    しやすい
    0.46
    ស្ស
    0.46
     ಪುಟ
    0.46
     пье
    0.46
    AttributedString
    0.46
    钺
    0.46
     রঙের
    0.45
     состави
    0.45
    POSITIVE LOGITS
    $
    0.47
     `
    0.44
     inheritance
    0.44
     Libert
    0.43
     badly
    0.43
     critically
    0.43
    iteration
    0.43
    amphetamine
    0.42
     incredible
    0.42
     incremento
    0.42
    Activations Density 0.000%

    No Known Activations