© 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. 11727
    Prev
    Next
    INDEX
    Explanations

    configuration, temperatures, highs, MyModel

    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
    ﺢ
    1.34
     previa
    1.26
    வியல்
    1.24
     Loksatta
    1.22
    ہور
    1.19
    Референце
    1.19
    شاركة
    1.19
    有哪些
    1.18
     tincidunt
    1.18
     fonbet
    1.17
    POSITIVE LOGITS
    de
    1.14
    the
    1.13
    त
    1.13
    emit
    1.12
    ان
    1.12
    ो
    1.11
    Quartz
    1.05
    tomato
    1.04
    te
    1.02
    rd
    1.02
    Activations Density 0.000%

    No Known Activations