© 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. 8873
    Prev
    Next
    INDEX
    Explanations

    table and list structures

    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
    𝑒
    2.51
    ्यारह
    1.95
    ore
    1.89
    ac
    1.88
    ót
    1.82
    RSA
    1.81
    𝑅
    1.78
     indist
    1.78
     gedaan
    1.74
    err
    1.74
    POSITIVE LOGITS
    ../../
    2.56
    ्स
    2.41
    서
    2.34
    اً
    2.30
    ా
    2.26
    ៊ី
    2.19
    ized
    2.17
    اف
    2.10
    ాన్ని
    2.10
    esque
    2.10
    Activations Density 0.038%

    No Known Activations