© 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. 11257
    Prev
    Next
    INDEX
    Explanations

    radiation and light waves

    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
     anniversary
    1.67
    น
    1.57
     older
    1.46
    (\
    1.43
    ید
    1.42
    ೃ
    1.40
    ativo
    1.39
     evitar
    1.39
     termo
    1.38
    жди
    1.37
    POSITIVE LOGITS
    ໄ
    1.75
     diethyl
    1.72
     mampu
    1.62
     Röntgen
    1.61
    t
    1.60
    ंध्र
    1.55
    裘
    1.53
     hypersur
    1.52
     frontier
    1.52
     sulfide
    1.52
    Activations Density 0.053%

    No Known Activations