© 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. 181871
    Prev
    Next
    INDEX
    Explanations

    bag, have, brave, worth

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

    lists, disjunctions, contrasts

    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
    獰
    0.57
    帳に追加
    0.47
    kowej
    0.46
    ̀ng
    0.45
     Versorgung
    0.45
    চনার
    0.45
    撾
    0.45
     serveur
    0.45
    द्वारे
    0.44
     அறிமுக
    0.44
    POSITIVE LOGITS
    这些
    0.46
    ↵
    0.43
     gauges
    0.42
    商标
    0.42
     FREE
    0.42
     welches
    0.42
     BEST
    0.41
    专利
    0.41
    م
    0.41
     endorsements
    0.40
    Activations Density 0.001%

    No Known Activations