© 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. 11562
    Prev
    Next
    INDEX
    Explanations

    back in time

    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
     vela
    1.31
    লী
    1.24
    পত্র
    1.21
    ﺏ
    1.18
    hearts
    1.17
    णु
    1.14
    તિ
    1.14
    铁
    1.14
    團
    1.14
    Verb
    1.14
    POSITIVE LOGITS
     snugly
    1.29
     lawful
    1.22
    kinawa
    1.21
     upcoming
    1.20
     Suzhou
    1.20
     ultrasound
    1.18
     Karlsson
    1.18
     sumptuous
    1.18
     exquisitely
    1.17
    灞
    1.16
    Activations Density 0.000%

    No Known Activations