© 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. 61631
    Prev
    Next
    INDEX
    Explanations

    numeric codes and symbols

    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
     weiß
    0.40
     self
    0.40
     white
    0.40
    ỡ
    0.39
     deity
    0.39
     White
    0.38
     teapot
    0.38
    White
    0.37
    gd
    0.37
     Robbins
    0.37
    POSITIVE LOGITS
    찹
    0.42
    痳
    0.42
    ╅
    0.40
    NCc
    0.39
    ControlType
    0.38
    ములో
    0.37
     दुर्गेश
    0.37
    Radiux
    0.37
     रूट
    0.37
     नियंत्रण
    0.37
    Activations Density 0.000%

    No Known Activations