© 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. 9-GEMMASCOPE-2-RES-262K
    7. 12399
    Prev
    Next
    INDEX
    Explanations

    commands with syntax

    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_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    er
    1.76
    י
    1.71
    e
    1.68
     ये
    1.61
    യാ
    1.56
     obliga
    1.50
    ার
    1.49
    election
    1.47
    ขัน
    1.46
    onbury
    1.46
    POSITIVE LOGITS
    🏾
    1.48
    🏼
    1.46
    ä
    1.45
    🏽
    1.43
    ../../
    1.35
    ../../../
    1.35
     gods
    1.34
     covariates
    1.33
    atively
    1.32
     credits
    1.32
    Activations Density 0.000%

    No Known Activations