© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28103
    Prev
    Next
    INDEX
    Explanations

    real world, perfect copies

    np_acts-logits-general · gemini-2.5-flash-lite

    large numbers with zeros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Feminist
    0.50
     Theology
    0.47
    halle
    0.46
     Stati
    0.46
    姣
    0.45
     Disability
    0.45
    相应的
    0.45
    炤
    0.44
     Lipid
    0.44
     Writing
    0.43
    POSITIVE LOGITS
     transcendence
    0.50
     vajj
    0.45
    erez
    0.45
     도시
    0.43
     vez
    0.43
     transcend
    0.41
     niz
    0.41
    ٪
    0.40
     evol
    0.39
    កំណ
    0.39
    Activations Density 0.000%

    No Known Activations