© 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. 183154
    Prev
    Next
    INDEX
    Explanations

    word followed by description

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

    customization instructions

    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
    0.52
     Walls
    0.42
    Walls
    0.40
     commodities
    0.39
    Unavailable
    0.39
     North
    0.39
     —
    0.39
    Transfer
    0.39
     MED
    0.38
    Mathemat
    0.38
    POSITIVE LOGITS
    밂
    0.54
    çok
    0.53
    鎴
    0.53
    ksyon
    0.53
    ὸ
    0.53
     littérature
    0.52
    {(-
    0.52
    ịt
    0.52
    stion
    0.52
    ẍ
    0.52
    Activations Density 0.000%

    No Known Activations