© 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. 126649
    Prev
    Next
    INDEX
    Explanations

    micro.blog, leads, mix, publicity

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

    questioning surprise or attraction

    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
     ہوگا۔
    0.48
     seront
    0.46
    ت
    0.45
     norte
    0.45
     serán
    0.44
     Asoci
    0.44
    ഹൃ
    0.44
     Experimental
    0.43
     regulations
    0.43
    هي
    0.42
    POSITIVE LOGITS
     लिहा
    0.47
     निभाया
    0.46
     पढ़ाया
    0.45
     писатель
    0.45
     सुना
    0.44
     другую
    0.44
     ณ
    0.44
     비슷한
    0.43
     लिया
    0.42
     दौरान
    0.42
    Activations Density 0.002%

    No Known Activations