© 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. 183958
    Prev
    Next
    INDEX
    Explanations

    let sit on

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

    phrases starting with certain words

    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
     ปลา
    0.49
     낮
    0.46
    xgb
    0.45
    evaluate
    0.44
     черно
    0.44
    htub
    0.44
     ಕ
    0.43
    ,-
    0.43
    ाना
    0.43
    carrito
    0.43
    POSITIVE LOGITS
    ണാ
    0.48
    ॉन्स
    0.48
     eux
    0.47
     bernama
    0.46
     multival
    0.44
    ुण
    0.44
     nærm
    0.43
    淀
    0.43
     sui
    0.43
     personas
    0.42
    Activations Density 0.001%

    No Known Activations