© 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. 51788
    Prev
    Next
    INDEX
    Explanations

    open file

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

    network token placing father tool

    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
     ಬಗ್ಗೆ
    0.51
     immoral
    0.50
     बारे
    0.49
    ও
    0.49
     मध्य
    0.48
     semua
    0.46
     ज़्यादा
    0.46
     tutti
    0.45
     todas
    0.44
     daripada
    0.44
    POSITIVE LOGITS
    ხ
    0.49
     Kb
    0.49
     Jane
    0.46
     Krem
    0.46
    Jane
    0.46
    nunique
    0.46
     révé
    0.45
     hón
    0.44
    ഫ
    0.43
     Zan
    0.42
    Activations Density 0.000%

    No Known Activations