© 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. 180081
    Prev
    Next
    INDEX
    Explanations

    property or proper care

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

    origins and connections

    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
     Scream
    0.45
     Phrase
    0.42
     रचनात्मक
    0.41
     Cheat
    0.41
    变
    0.41
     Password
    0.41
    写法
    0.40
     irrever
    0.40
     diễn
    0.39
     перемен
    0.39
    POSITIVE LOGITS
    EFI
    0.55
     EFI
    0.52
    UT
    0.47
    that
    0.46
     remnants
    0.45
    숴
    0.44
    ンダ
    0.44
     munitions
    0.44
    يروس
    0.44
    Nuclear
    0.42
    Activations Density 0.001%

    No Known Activations