© 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. 58480
    Prev
    Next
    INDEX
    Explanations

    safely and securely

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

    following sections or paragraphs

    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
     যুক্তি
    0.54
    的名字
    0.52
    У
    0.50
    Fr
    0.47
    名字
    0.46
    Ю
    0.46
    Ú
    0.45
    থন
    0.44
    Args
    0.43
    acağını
    0.43
    POSITIVE LOGITS
    aient
    0.52
     Currents
    0.52
     policymakers
    0.51
    ass
    0.49
     Graduates
    0.49
     Ass
    0.48
     auteurs
    0.48
    ilyn
    0.47
     graduates
    0.47
     monasteries
    0.46
    Activations Density 0.001%

    No Known Activations