© 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. 225422
    Prev
    Next
    INDEX
    Explanations

    moving stuff, solar cells, transfer stations

    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
     受け
    0.47
    device
    0.44
    ométrie
    0.42
    dispatch
    0.41
    ]]);
    0.41
    scheduling
    0.41
     *)
    0.40
     କରି
    0.40
    년을
    0.40
    each
    0.40
    POSITIVE LOGITS
     ehemal
    0.47
    醋
    0.45
    اف
    0.43
     Stewart
    0.43
    োনাম
    0.42
    啤酒
    0.42
    紅色
    0.42
    ాల్
    0.41
    Ꮘ
    0.41
     Schloss
    0.41
    Activations Density 0.001%

    No Known Activations