© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8230
    Prev
    Next
    INDEX
    Explanations

    body shape, stature, and weight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    💿
    0.63
     philosoph
    0.53
     dépôt
    0.53
     zond
    0.53
    🥁
    0.53
     behavior
    0.52
     domain
    0.51
     awesome
    0.51
    情绪
    0.51
    👄
    0.51
    POSITIVE LOGITS
     estatura
    1.37
     physique
    1.32
    身高
    1.24
    身材
    1.23
     physiques
    1.20
     stature
    1.19
    体重
    1.18
     slender
    1.13
    身長
    1.12
    身体
    1.11
    Activations Density 0.509%

    No Known Activations