© 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. 31278
    Prev
    Next
    INDEX
    Explanations

    Dark Tokyo

    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
     dispersions
    0.38
     જન્મદિવસ
    0.38
    鰯
    0.37
    ု
    0.36
     triples
    0.34
    avkh
    0.34
    auti
    0.34
     αγ
    0.34
    িষ্ট
    0.33
    哇
    0.33
    POSITIVE LOGITS
     Created
    0.41
     No
    0.38
    പു
    0.38
     Walker
    0.38
    corner
    0.38
     Pause
    0.38
     Rem
    0.37
     Walk
    0.37
     Metaverse
    0.37
    No
    0.36
    Activations Density 0.003%

    No Known Activations