© 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. 147765
    Prev
    Next
    INDEX
    Explanations

    website, fighting, testing

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

    command-line tool, helpful, UI

    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
     cavité
    0.46
    🥩
    0.46
     poprzez
    0.45
    チューブ
    0.45
    籮
    0.45
    ercase
    0.44
     Billy
    0.44
     вдох
    0.44
    s
    0.43
     chcia
    0.43
    POSITIVE LOGITS
    ój
    0.49
     delusion
    0.48
    жден
    0.46
     persist
    0.46
    apper
    0.44
    ensen
    0.44
    odic
    0.44
     persistent
    0.42
    kon
    0.42
    istically
    0.42
    Activations Density 0.001%

    No Known Activations