© 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. 67065
    Prev
    Next
    INDEX
    Explanations

    common phrasal components

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

    planner, increasingly, file, depends, considering

    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
    띠
    0.51
    erra
    0.48
    zoom
    0.45
    leden
    0.45
    lev
    0.44
    seite
    0.43
    houd
    0.42
     is
    0.42
    spreadsheet
    0.42
     gled
    0.42
    POSITIVE LOGITS
     सुकून
    0.49
     安心
    0.47
     哦
    0.45
     Shadows
    0.44
    收购
    0.43
     其
    0.43
    殇
    0.43
    ',['
    0.43
    搭載
    0.43
     INITIAL
    0.43
    Activations Density 0.001%

    No Known Activations