© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11923
    Prev
    Next
    INDEX
    Explanations

    material, emotions, or app contexts

    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
    きた
    1.29
    цца
    1.17
    িতে
    1.14
    burg
    1.10
    きて
    1.07
    ى
    1.06
    َ
    0.99
     Именно
    0.99
    iniz
    0.99
    𝚔
    0.98
    POSITIVE LOGITS
    elfth
    1.47
    dwell
    1.36
    tyard
    1.33
     commemorating
    1.31
    reiro
    1.31
     endangered
    1.30
     zebrafish
    1.29
    <unused936>
    1.29
     Arabidopsis
    1.29
     unes
    1.29
    Activations Density 0.001%

    No Known Activations