© 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. 169153
    Prev
    Next
    INDEX
    Explanations

    business transactions and ideas

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

    theft, blue, gray, boolean, been, sides

    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
    劇情
    0.54
    幵
    0.52
    Upload
    0.50
    enthalt
    0.50
    Squ
    0.48
    紀錄
    0.48
     पहा
    0.46
    Encoder
    0.46
    \<^
    0.46
     पाहि
    0.46
    POSITIVE LOGITS
     volumes
    0.52
     financiación
    0.52
     unlabeled
    0.52
     inversiones
    0.52
     needles
    0.51
     competencia
    0.51
    0.50
     estrella
    0.49
     financing
    0.49
     banknotes
    0.49
    Activations Density 0.000%

    No Known Activations