© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2826
    Prev
    Next
    INDEX
    Explanations

    heat, design, sufficient, skin, Hornet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     disrupt
    0.41
     debates
    0.38
    是由
    0.38
     Emperor
    0.38
    shaw
    0.38
     explored
    0.38
     lark
    0.38
    由
    0.37
    营造
    0.37
    扎
    0.37
    POSITIVE LOGITS
    cursor
    0.42
    organisme
    0.41
    Brett
    0.41
    ítja
    0.41
     manualmente
    0.40
     Subscriber
    0.40
     দর্শকের
    0.40
    Headline
    0.39
    блема
    0.39
    Magnet
    0.39
    Activations Density 0.010%

    No Known Activations