© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3121
    Prev
    Next
    INDEX
    Explanations

    directions and spatial relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     statutory
    0.61
    <unused933>
    0.61
     mis
    0.60
     skór
    0.60
     プラ
    0.60
     lagen
    0.59
    ையில்
    0.59
    蛻
    0.59
     Statutory
    0.58
    okhlov
    0.58
    POSITIVE LOGITS
     left
    2.62
    left
    2.29
    左
    2.27
    Left
    2.21
     north
    2.19
     Left
    2.13
     west
    2.13
     east
    2.10
    右
    2.10
    LEFT
    2.09
    Activations Density 0.265%

    No Known Activations