© 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. 187666
    Prev
    Next
    INDEX
    Explanations

    labels, business, services, information

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

    playlist, Authenticator, Solutions, URLs

    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
     खासा
    0.49
     धो
    0.45
    ুতে
    0.45
     बुल
    0.44
    aving
    0.44
    活
    0.42
    র্প
    0.41
    raged
    0.41
    していく
    0.41
     swapped
    0.41
    POSITIVE LOGITS
    ীদার
    0.50
    courses
    0.48
    䍩
    0.46
    צ
    0.46
     MILLER
    0.44
    korn
    0.44
    وڑ
    0.44
    g
    0.44
     يون
    0.43
    ceding
    0.43
    Activations Density 0.000%

    No Known Activations