© 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. 106173
    Prev
    Next
    INDEX
    Explanations

    US history

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

    code snippet

    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
     pago
    0.52
     വഴ
    0.51
     estación
    0.49
     gönder
    0.48
     parro
    0.48
     siendo
    0.48
     papá
    0.47
     お
    0.47
     polícia
    0.47
     फूल
    0.47
    POSITIVE LOGITS
    프로
    0.42
    ตะ
    0.42
    dual
    0.41
    ਚ
    0.41
    ODA
    0.40
    Throughout
    0.40
     العملية
    0.40
    วาง
    0.39
    acceptance
    0.39
    োদ
    0.39
    Activations Density 0.007%

    No Known Activations