© 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. 188501
    Prev
    Next
    INDEX
    Explanations

    Soviet aerospace

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

    history to malaria-endemic area

    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
    idy
    0.45
    льная
    0.44
    acity
    0.43
     liés
    0.42
    留
    0.41
    也很
    0.41
    otion
    0.40
    ,
    0.40
    별
    0.40
     Endpoint
    0.40
    POSITIVE LOGITS
     IAAF
    0.60
     ২০১২
    0.59
     تحقيق
    0.57
     ২০১১
    0.47
     JAMA
    0.47
     FISA
    0.47
     ought
    0.46
     ২০১৩
    0.46
    GoAbroad
    0.46
     riconosci
    0.46
    Activations Density 0.006%

    No Known Activations