© 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. 41-GEMMASCOPE-2-RES-262K
    7. 22593
    Prev
    Next
    INDEX
    Explanations

    words starting with "wh"

    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_all/layer_41_width_262k_l0_big
    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
     функ
    0.49
    ान्य
    0.44
     обору
    0.41
    ंनो
    0.38
     Importantly
    0.38
    刂
    0.38
    acji
    0.37
     लागि
    0.37
    诺
    0.36
    ņi
    0.36
    POSITIVE LOGITS
    Wh
    0.87
     wh
    0.85
    wh
    0.83
     Wh
    0.77
     whirl
    0.62
     whistling
    0.61
     whist
    0.59
    Whi
    0.59
     whistle
    0.58
     WH
    0.58
    Activations Density 0.006%

    No Known Activations