© 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-16K
    7. 2592
    Prev
    Next
    INDEX
    Explanations

    than and comparison

    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_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
    𝗮
    1.47
    ي
    1.45
    𝗶
    1.44
    𝗲
    1.42
    𝗸
    1.34
    тли
    1.33
    t
    1.30
    л
    1.28
    𝘀
    1.26
    י
    1.26
    POSITIVE LOGITS
     Перейти
    1.28
     Inoltre
    1.23
    cao
    1.21
    на
    1.17
    ca
    1.13
    <unused2164>
    1.12
    перь
    1.10
     становништво
    1.10
    한편
    1.08
     portrayed
    1.08
    Activations Density 0.093%

    No Known Activations