© 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-262K
    7. 5440
    Prev
    Next
    INDEX
    Explanations

    logline

    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_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
     obs
    0.39
     пре
    0.38
     n
    0.37
     os
    0.36
    ulp
    0.36
     hence
    0.36
     works
    0.36
     thus
    0.35
     по
    0.35
     age
    0.35
    POSITIVE LOGITS
    <unused2074>
    0.48
    ICIENCY
    0.47
    Cryptography
    0.46
     nhàng
    0.46
    IZATION
    0.45
    withstanding
    0.45
    คัญ
    0.44
    Beau
    0.44
    <unused520>
    0.43
    MENTS
    0.43
    Activations Density 0.831%

    No Known Activations