© 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. 79762
    Prev
    Next
    INDEX
    Explanations

    Big Island

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

    states and transitions

    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
    BA
    0.46
    出来
    0.45
     wastage
    0.45
    ゅ
    0.45
     サングラス
    0.43
    lived
    0.43
    ชีวิต
    0.42
     životu
    0.42
     assassin
    0.42
     acclimat
    0.41
    POSITIVE LOGITS
    সংস্কার
    0.46
    istä
    0.45
     fünf
    0.43
    涕
    0.43
     setNew
    0.43
     sechs
    0.42
    uert
    0.42
     féidir
    0.42
     Mex
    0.41
     Truly
    0.41
    Activations Density 0.001%

    No Known Activations