© 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. 159935
    Prev
    Next
    INDEX
    Explanations

    disposal ATMs indicators

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

    tools and methods

    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
     Announcement
    0.59
    (
    0.56
    ?)
    0.55
    y
    0.55
    ం
    0.52
    人
    0.51
     Maximum
    0.49
    **)
    0.49
    *)(
    0.49
    ?),
    0.48
    POSITIVE LOGITS
    过于
    0.57
     بواسطة
    0.57
     ferramenta
    0.55
     outils
    0.51
     ഉപകരണ
    0.51
    chées
    0.50
     புகைப்பட
    0.49
     通过
    0.48
    fähig
    0.48
     belieb
    0.48
    Activations Density 0.000%

    No Known Activations