© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8918
    Prev
    Next
    INDEX
    Explanations

    Gaussian blur, kernel size, sigma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     команд
    0.57
    崆
    0.52
    =".
    0.47
    ंपूर्
    0.47
     utilize
    0.47
     интервью
    0.46
    чук
    0.46
     ።
    0.46
     calorimetric
    0.46
     रेशियो
    0.46
    POSITIVE LOGITS
     terem
    0.45
     B
    0.44
     banyaknya
    0.44
     fez
    0.43
     wal
    0.43
     morgen
    0.42
    ley
    0.42
     I
    0.42
     fast
    0.41
     foi
    0.41
    Activations Density 0.001%

    No Known Activations