© 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. 249674
    Prev
    Next
    INDEX
    Explanations

    types of things

    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
    并通过
    0.54
    I
    0.52
    Be
    0.50
    Operational
    0.48
    е
    0.46
    Cox
    0.46
    Luck
    0.46
    得
    0.45
    j
    0.45
    Assistant
    0.45
    POSITIVE LOGITS
    ಾಗಿ
    0.58
     relics
    0.57
     cunning
    0.57
     hates
    0.54
     lensa
    0.53
     timelapse
    0.52
     versi
    0.52
     naszych
    0.52
     PT
    0.51
     punish
    0.50
    Activations Density 0.000%

    No Known Activations