© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2194
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    tains
    1.25
    eers
    1.07
     daya
    1.04
    xu
    1.01
     inward
    0.97
    EK
    0.97
    憎
    0.97
    SJ
    0.97
    tained
    0.97
    EVER
    0.96
    POSITIVE LOGITS
    ویں
    1.17
    ळे
    1.13
     वीं
    1.13
     th
    1.09
     tumb
    1.09
     striées
    1.09
    éré
    1.08
     novembre
    1.07
    onRouteChange
    1.07
    インチ
    1.07
    Activations Density 0.554%

    No Known Activations