© 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. 149409
    Prev
    Next
    INDEX
    Explanations

    increase footfall

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

    bow tie, shutdown, predicted values, move on, aligning data, Japanese fandom

    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
     Planung
    0.49
     PLANNING
    0.49
    赈
    0.48
     Planning
    0.46
    깊
    0.46
     váll
    0.45
    inker
    0.45
    
    0.45
    Planning
    0.44
     سجل
    0.43
    POSITIVE LOGITS
    ra
    0.58
    f
    0.55
    re
    0.53
    ft
    0.53
    j
    0.52
    r
    0.52
    ve
    0.51
    tt
    0.49
    time
    0.49
    bar
    0.48
    Activations Density 0.000%

    No Known Activations