© 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. 73816
    Prev
    Next
    INDEX
    Explanations

    evaluating its feasibility

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

    elaborate on technologies

    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
     врач
    0.54
    ：“
    0.50
    ैव
    0.47
    образ
    0.47
     amounting
    0.46
    ンプル
    0.46
    ﺤ
    0.45
     остаются
    0.45
    ▥
    0.45
    으로서
    0.44
    POSITIVE LOGITS
     fen
    0.56
     port
    0.49
     prelimin
    0.48
     Porto
    0.46
     mainMenu
    0.45
    gra
    0.44
     centri
    0.43
     porte
    0.43
    start
    0.43
     eer
    0.43
    Activations Density 0.000%

    No Known Activations