© 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. 30830
    Prev
    Next
    INDEX
    Explanations

    letters and character codes

    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
    風味
    0.51
    溶
    0.46
    牝
    0.46
     racemic
    0.44
    紘
    0.42
     rac
    0.41
    合物
    0.41
    ψη
    0.40
    รรม
    0.40
    DUCT
    0.39
    POSITIVE LOGITS
    9
    0.65
    6
    0.56
     Letter
    0.55
    8
    0.53
     Lawn
    0.51
     Ord
    0.48
     letter
    0.48
     lettera
    0.48
    ord
    0.47
     byte
    0.47
    Activations Density 0.007%

    No Known Activations