© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9687
    Prev
    Next
    INDEX
    Explanations

    examples and context

    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
    u
    1.35
     Arabic
    1.15
     Tw
    1.12
     Mathematical
    1.07
     Working
    1.07
    т
    1.05
     Faith
    1.03
    quela
    1.03
     Trabal
    1.03
     Pearson
    1.03
    POSITIVE LOGITS
     listrik
    1.38
    其實
    1.32
    herd
    1.31
    例如
    1.29
     yerden
    1.28
    從
    1.22
    শ
    1.21
    其实
    1.18
     kanamycin
    1.18
     particulates
    1.18
    Activations Density 0.000%

    No Known Activations