© 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. 9904
    Prev
    Next
    INDEX
    Explanations

    it's

    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
    i
    1.43
    in
    1.32
     extremos
    1.29
     Radius
    1.27
     relativ
    1.25
     distanc
    1.25
     marques
    1.19
     décadas
    1.19
     suunn
    1.17
     attra
    1.17
    POSITIVE LOGITS
    skipped
    1.21
    ε
    1.11
    proclaimed
    1.10
    composed
    1.09
     cohomology
    1.09
    referred
    1.08
    nouns
    1.06
     Например
    1.05
    sns
    1.05
    alej
    1.04
    Activations Density 0.000%

    No Known Activations