© 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. 71251
    Prev
    Next
    INDEX
    Explanations

    multiples slots browse merchants

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

    actions and objects

    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
     Cách
    0.50
     cách
    0.47
    Cách
    0.47
    lifts
    0.44
     Πολ
    0.44
     Phần
    0.44
     Если
    0.43
    Δ
    0.42
    uur
    0.42
     झाल
    0.42
    POSITIVE LOGITS
     فیصلے
    0.45
     Radcliffe
    0.41
     defeat
    0.41
     iran
    0.41
     arrest
    0.40
     posit
    0.40
     novos
    0.40
     Majority
    0.40
    mdan
    0.40
    reichen
    0.39
    Activations Density 0.000%

    No Known Activations