© 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. 195694
    Prev
    Next
    INDEX
    Explanations

    clear focus

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

    types, secret, symbols, portal

    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
     বঙ্গবন্ধু
    0.56
    INTa
    0.56
     खींचो
    0.51
     這個
    0.51
     besitzt
    0.50
     Плавание
    0.50
     長
    0.49
     เชื่อ
    0.49
     อัน
    0.48
    當然
    0.48
    POSITIVE LOGITS
     You
    0.52
     It
    0.47
     We
    0.47
    ,
    0.47
     (
    0.44
     an
    0.44
     Fractional
    0.44
    á
    0.43
     IL
    0.42
     parli
    0.42
    Activations Density 0.000%

    No Known Activations