© 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. 160955
    Prev
    Next
    INDEX
    Explanations

    specific numerical lists

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

    short contextual phrases

    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
    ਨਾ
    0.52
     үч
    0.46
     pcMove
    0.44
     cod
    0.44
    เที่ยว
    0.44
    ادث
    0.42
    駙
    0.42
    とのこと
    0.42
     roadblock
    0.42
    灝
    0.41
    POSITIVE LOGITS
     নিয়ত
    0.48
     والس
    0.48
    ش
    0.48
    al
    0.48
     ويم
    0.46
     fühlen
    0.45
     Contract
    0.45
     Covered
    0.44
     مغ
    0.44
     Sum
    0.44
    Activations Density 0.000%

    No Known Activations