© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9490
    Prev
    Next
    INDEX
    Explanations

    links and scientific identifiers

    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
    ur
    1.47
    ش
    1.27
    🏼
    1.25
    F
    1.21
    charAt
    1.20
    峨
    1.20
    T
    1.19
    L
    1.14
    P
    1.13
    rin
    1.13
    POSITIVE LOGITS
    ۱۳
    1.39
     fazia
    1.31
     previamente
    1.30
     pptn
    1.28
    삵
    1.28
    τία
    1.27
     stockbild
    1.26
     zealand
    1.26
    ۱۲
    1.26
    लया
    1.26
    Activations Density 0.005%

    No Known Activations