© 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. 23053
    Prev
    Next
    INDEX
    Explanations

    development of

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

    visa and permit requirements

    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
    1
    0.51
    4
    0.51
     NUMBER
    0.50
    3
    0.48
     that
    0.47
    5
    0.46
     which
    0.46
    ที่จะ
    0.46
     প্রশ্ন
    0.45
     possano
    0.45
    POSITIVE LOGITS
     postwar
    0.46
    🏡
    0.46
     yalnız
    0.42
     الجميع
    0.42
    ďaka
    0.40
     zahval
    0.40
     njegov
    0.40
    payers
    0.40
    fueled
    0.40
    getcwd
    0.39
    Activations Density 0.000%

    No Known Activations