© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9054
    Prev
    Next
    INDEX
    Explanations

    force and direction

    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
    akad
    0.37
     কাঠ
    0.36
    лер
    0.36
    環境
    0.36
    ń
    0.35
    kow
    0.34
     strukt
    0.34
     :/
    0.34
    ظيف
    0.34
    \
    0.33
    POSITIVE LOGITS
     direction
    0.60
     intensity
    0.47
     directions
    0.46
    方向
    0.46
    direction
    0.45
     intensities
    0.45
     directional
    0.45
    intensity
    0.44
     magnitude
    0.43
     направление
    0.43
    Activations Density 0.000%

    No Known Activations