© 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. 1761
    Prev
    Next
    INDEX
    Explanations

    character class and abilities

    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
     residues
    0.59
     olefins
    0.55
     isotropic
    0.55
     iccad
    0.55
    াত্মক
    0.54
    ើយ
    0.54
     idxf
    0.53
    <unused311>
    0.53
    ាប
    0.52
    runoff
    0.52
    POSITIVE LOGITS
     Skills
    0.64
     Constitution
    0.63
     class
    0.62
     Fighter
    0.62
     Classes
    0.60
     Spiritual
    0.60
     Religion
    0.59
     Racial
    0.57
     classes
    0.56
     Dexter
    0.56
    Activations Density 0.024%

    No Known Activations