© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 197888
    Prev
    Next
    INDEX
    Explanations

    planet, rocket, prose

    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
    愛情
    0.41
    🌵
    0.40
    mixin
    0.39
    仙
    0.39
    ebab
    0.38
     auff
    0.38
     Fairy
    0.38
     saben
    0.38
     रक्षाबंधनाच्या
    0.37
    🧀
    0.37
    POSITIVE LOGITS
    cim
    0.44
    __)
    0.43
    —.
    0.42
     —,
    0.39
    __:
    0.38
     MM
    0.38
    HN
    0.38
     —
    0.37
     __
    0.37
    **)
    0.37
    Activations Density 0.149%

    No Known Activations