© 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. 252348
    Prev
    Next
    INDEX
    Explanations

    explaining choices and options

    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
    根據
    0.54
    珽
    0.53
    東京
    0.52
    ﺙ
    0.52
    ﺱ
    0.52
    تی
    0.52
    ニン
    0.51
    息子
    0.51
    Seth
    0.51
    Ο
    0.51
    POSITIVE LOGITS
     gritty
    0.55
     massacre
    0.50
     abuses
    0.49
     mouseDown
    0.48
     bushy
    0.48
     militia
    0.48
     reflective
    0.48
     breezy
    0.47
     dennoch
    0.47
     душу
    0.46
    Activations Density 0.001%

    No Known Activations