© 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. 91250
    Prev
    Next
    INDEX
    Explanations

    volition, desire, intent

    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
    세대
    0.51
    tgt
    0.46
    z
    0.45
    landır
    0.44
    支持
    0.44
    n
    0.44
    ကျ
    0.43
     mùi
    0.43
    חיל
    0.43
    𒈗
    0.43
    POSITIVE LOGITS
     wills
    0.56
    Wishing
    0.54
     vontade
    0.54
    Resolution
    0.52
    Disposition
    0.52
    Will
    0.51
    Wish
    0.50
     voluntad
    0.50
     volontà
    0.49
     desires
    0.46
    Activations Density 0.027%

    No Known Activations