© 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. 123755
    Prev
    Next
    INDEX
    Explanations

    financial or institutional actions

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

    principle to tagging data

    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
    Negative Logits
     Fahrzeug
    0.43
     ঘটে
    0.43
    されていない
    0.42
     darwin
    0.42
    Increment
    0.42
     externally
    0.41
    ,$
    0.41
    版本的
    0.41
     noch
    0.40
    сия
    0.40
    POSITIVE LOGITS
     खेलों
    0.49
     sketches
    0.48
     सुपरहिट
    0.46
    脱毛
    0.45
    р
    0.45
    leich
    0.45
     Melrose
    0.44
    ana
    0.44
    apayati
    0.44
    ારીખ
    0.44
    Activations Density 0.000%

    No Known Activations