© 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. 2613
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and code

    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
    schaft
    3.10
    <bos>
    2.74
    tint
    2.49
    ሚ
    2.43
     SKSpriteNode
    2.41
     relent
    2.35
    categorie
    2.34
    ամ
    2.32
    schirm
    2.30
    তি
    2.29
    POSITIVE LOGITS
    เป็น
    2.59
    ct
    2.57
    л
    2.53
    σή
    2.51
    ctive
    2.44
    T
    2.43
    $,
    2.42
    لا
    2.41
    se
    2.40
    voor
    2.40
    Activations Density 0.547%

    No Known Activations