© 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. 147994
    Prev
    Next
    INDEX
    Explanations

    time and contest

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

    tax reporting, optimization, nature, data, instructions

    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
    congestion
    0.53
    밝
    0.50
    ಿಸ್ಟ
    0.47
    masht
    0.46
    미
    0.46
    버
    0.46
    ፁ
    0.46
    spj
    0.46
    ין
    0.46
    매
    0.46
    POSITIVE LOGITS
     Remember
    0.46
    介紹
    0.46
     بنانے
    0.45
     Пла
    0.44
    án
    0.44
     Heat
    0.44
     മനസ
    0.44
     relative
    0.44
     Pré
    0.43
    વવા
    0.42
    Activations Density 0.001%

    No Known Activations