© 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. 11037
    Prev
    Next
    INDEX
    Explanations

    blanket and related comfort items

    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
    क
    2.62
    т
    2.37
    犸
    2.24
    sic
    2.17
    น์
    2.15
    cancelled
    2.12
    broke
    2.12
    в
    2.12
    k
    2.10
    н
    2.10
    POSITIVE LOGITS
    帼
    2.69
     frankly
    2.64
     shawl
    2.47
     scarves
    2.39
    𝐲
    2.39
    ⨯
    2.37
    ../../
    2.36
     riddled
    2.33
     seleccione
    2.33
    拉斯
    2.33
    Activations Density 0.027%

    No Known Activations