© 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. 132788
    Prev
    Next
    INDEX
    Explanations

    award nominees

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

    leading indicators

    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
     عند
    0.52
    婳
    0.52
     Resultado
    0.50
     expressão
    0.48
    íg
    0.47
    abor
    0.47
     显示
    0.47
    众
    0.46
     面
    0.46
     Roswell
    0.46
    POSITIVE LOGITS
    Ｙ
    0.49
    ᱑
    0.48
    летний
    0.47
    enstein
    0.46
    ികി
    0.46
    ኔታ
    0.45
    তিপ
    0.44
    はよう
    0.44
    ಕಾಶ
    0.44
    に取り組
    0.44
    Activations Density 0.000%

    No Known Activations