© 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. 12234
    Prev
    Next
    INDEX
    Explanations

    Javascript import statements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    etään
    2.19
    ங்கிணை
    1.93
    et
    1.85
     viewController
    1.72
     cmds
    1.72
    /−
    1.70
     Vis
    1.70
     repetition
    1.68
    yd
    1.68
    лук
    1.67
    POSITIVE LOGITS
    ानुसार
    1.66
    swear
    1.64
    |\
    1.61
    ных
    1.58
    ively
    1.58
    ajat
    1.56
     supervising
    1.56
    tenance
    1.56
    izations
    1.55
    ünün
    1.55
    Activations Density 0.003%

    No Known Activations