© 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. 31793
    Prev
    Next
    INDEX
    Explanations

    sealing process

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

    releases a, understand risks

    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
     কৃ
    0.54
    |_{\
    0.53
    \}=\
    0.50
     ກຳ
    0.49
     TEMPERATURE
    0.49
     மிகப்பெ
    0.48
     בא
    0.47
     に対
    0.47
     ジェ
    0.47
    possibleTypes
    0.47
    POSITIVE LOGITS
    ي
    0.46
    imension
    0.42
    an
    0.42
    rim
    0.41
     dozen
    0.41
    iunea
    0.41
    unar
    0.40
    ليل
    0.40
    يلا
    0.40
    un
    0.39
    Activations Density 0.000%

    No Known Activations