© 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. 251394
    Prev
    Next
    INDEX
    Explanations

    academic subjects and roles

    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
    ค
    0.48
    WORKS
    0.45
    ワーク
    0.45
    之上
    0.44
    餐
    0.44
    ذ
    0.44
    Ash
    0.43
    震
    0.43
    Template
    0.43
    布
    0.43
    POSITIVE LOGITS
    ຜະລິດຕະພັນ
    0.49
     jubil
    0.47
     situ
    0.46
    rzym
    0.46
     yani
    0.46
     Kiến
    0.45
    onian
    0.45
     в
    0.44
     inaugur
    0.44
    និង
    0.44
    Activations Density 0.001%

    No Known Activations