© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99423
    Prev
    Next
    INDEX
    Explanations

    revised menu

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

    father does

    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
    濕
    0.49
     dígitos
    0.48
     irrepar
    0.47
    讀
    0.47
    vrdr
    0.46
     azy
    0.46
    餒
    0.45
    ൃ
    0.44
     watts
    0.44
     profusely
    0.43
    POSITIVE LOGITS
    argin
    0.49
     arginine
    0.47
    তুন
    0.44
    Potion
    0.44
     украин
    0.43
    Ukrainian
    0.43
    ucchini
    0.43
    Corner
    0.43
    tape
    0.43
    horizon
    0.42
    Activations Density 0.000%

    No Known Activations