© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 231315
    Prev
    Next
    INDEX
    Explanations

    car completion or lack thereof

    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
    嶌
    0.50
    มัน
    0.49
     він
    0.49
    ມັນ
    0.48
    པ
    0.48
     двух
    0.48
     Drucker
    0.48
    нци
    0.47
     CELLS
    0.47
    ྥ
    0.47
    POSITIVE LOGITS
    d
    0.59
    et
    0.53
    dur
    0.52
    ramble
    0.49
    ifting
    0.47
    Village
    0.47
    getattr
    0.47
    dirt
    0.47
     સાં
    0.47
     Ramb
    0.46
    Activations Density 0.001%

    No Known Activations