© 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. 186312
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    FAQs, Negotiation, Descent, Ideas, Chronic

    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
    '
    0.52
     tablespoons
    0.48
     textures
    0.46
     Κ
    0.45
    Delegate
    0.45
     травня
    0.45
     fillets
    0.45
     delegates
    0.44
    、、、
    0.44
    ิทธิ์
    0.43
    POSITIVE LOGITS
    菄
    0.52
     حي
    0.50
    䡛
    0.50
     futuros
    0.49
     aliran
    0.48
    ارة
    0.48
     الحي
    0.47
    䄸
    0.46
     largos
    0.46
     vivir
    0.45
    Activations Density 0.000%

    No Known Activations