© 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. 28883
    Prev
    Next
    INDEX
    Explanations

    yes/no questions

    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
    也就是说
    0.41
     we
    0.40
     내가
    0.40
     hacemos
    0.40
     storyteller
    0.39
    뻤
    0.38
     drugim
    0.38
     RELATION
    0.38
    ⌛
    0.38
     timing
    0.38
    POSITIVE LOGITS
     خلال
    0.46
     بطور
    0.46
     مجبور
    0.44
     പേ
    0.43
    这款
    0.43
    ิมพ์
    0.42
     لهذه
    0.42
     exile
    0.42
     هنگام
    0.41
     यावेळी
    0.41
    Activations Density 0.000%

    No Known Activations