© 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. 49405
    Prev
    Next
    INDEX
    Explanations

    "the" followed by nouns

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

    Spanish and English education

    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
    用
    0.55
    미
    0.55
    中國
    0.55
    紅
    0.55
    美國
    0.54
    用戶
    0.53
    圖
    0.53
    И
    0.52
    ل
    0.52
    人性
    0.51
    POSITIVE LOGITS
     destroyed
    0.44
     Herman
    0.44
     scrambled
    0.43
     Hartman
    0.43
     attributable
    0.43
     HSV
    0.43
     cutter
    0.43
     discriminatory
    0.42
     AHA
    0.42
     Cushion
    0.42
    Activations Density 0.000%

    No Known Activations