© 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. 217126
    Prev
    Next
    INDEX
    Explanations

    Gold Package, Silver Package

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

    special characters or formatting

    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
    immt
    0.47
     पोजीशन
    0.46
     टकराव
    0.46
    immers
    0.44
    ekš
    0.44
     센터
    0.44
    뜨
    0.43
     ignited
    0.43
     überprü
    0.43
     kristall
    0.43
    POSITIVE LOGITS
    ση
    0.51
    FOR
    0.50
    вра
    0.50
    Hr
    0.49
    FORM
    0.48
    皓
    0.48
    ть
    0.46
    LETTER
    0.46
    TR
    0.45
    PERSON
    0.44
    Activations Density 0.001%

    No Known Activations