© 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. 110533
    Prev
    Next
    INDEX
    Explanations

    following regulations or advice

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

    Scientists, Relatively, remote, attract, prompted

    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
    ينية
    0.52
    사각형
    0.49
    пу
    0.46
    절
    0.46
    留在
    0.46
    จาก
    0.45
     entitle
    0.45
    لة
    0.45
    페
    0.45
    ಡುಗೆ
    0.43
    POSITIVE LOGITS
     दहशत
    0.52
    atm
    0.47
     li
    0.46
     sieben
    0.45
    𝖺
    0.44
     இந்தப்
    0.43
     मेहता
    0.43
    vak
    0.43
     चीफ
    0.43
    áme
    0.42
    Activations Density 0.002%

    No Known Activations