© 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. 11128
    Prev
    Next
    INDEX
    Explanations

    Have them create

    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
    ura
    1.26
     storied
    1.22
     ras
    1.18
     harus
    1.18
    ٓ
    1.17
    ب
    1.17
    unsqueeze
    1.16
    𝕣
    1.14
    くれる
    1.13
    ‍
    1.12
    POSITIVE LOGITS
     início
    1.47
    نساء
    1.39
    ات
    1.39
     evasion
    1.30
     exquisitely
    1.29
     convivencia
    1.28
     incubator
    1.28
    s
    1.27
     invigor
    1.27
     souvenirs
    1.27
    Activations Density 0.000%

    No Known Activations