© 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. 225930
    Prev
    Next
    INDEX
    Explanations

    international threat

    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
    ษัท
    0.47
     existential
    0.46
    bered
    0.44
    එ
    0.44
    fø
    0.43
    延长
    0.42
    岁月
    0.42
    blown
    0.41
    くり
    0.41
    thorn
    0.41
    POSITIVE LOGITS
     熱
    0.52
     紹介
    0.50
    ężczy
    0.49
     소개
    0.49
    মুখ
    0.48
    CCSD
    0.47
     省
    0.46
    UMIN
    0.45
     اط
    0.45
     Quadrupèdes
    0.44
    Activations Density 0.001%

    No Known Activations