© 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. 23657
    Prev
    Next
    INDEX
    Explanations

    seals and sea lions

    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
     recicl
    0.42
    做好
    0.41
     πο
    0.41
    箪
    0.40
     ট্রে
    0.40
    proton
    0.39
     vazio
    0.39
    色素
    0.38
    衩
    0.38
    噤
    0.38
    POSITIVE LOGITS
     seals
    1.19
     Seals
    1.14
     seal
    1.10
     Seal
    1.05
    Seal
    1.04
     SEAL
    0.93
    seal
    0.88
    シール
    0.68
     otter
    0.63
     sealing
    0.62
    Activations Density 0.003%

    No Known Activations