© 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. 229166
    Prev
    Next
    INDEX
    Explanations

    know and love

    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
    艶
    0.49
    בוע
    0.46
    בע
    0.45
    עי
    0.45
    으며
    0.44
     λα
    0.44
     finir
    0.44
     מז
    0.44
    iyordu
    0.44
    <0xBF>
    0.44
    POSITIVE LOGITS
    颏
    0.47
     compensates
    0.47
     комплект
    0.46
     加工
    0.46
     integrate
    0.45
     kontaktu
    0.45
     authorizes
    0.43
    )}-
    0.43
     aé
    0.43
    🧺
    0.43
    Activations Density 0.000%

    No Known Activations