© 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. 132962
    Prev
    Next
    INDEX
    Explanations

    dependence

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

    living and conscious

    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
     Library
    0.50
     calligraphy
    0.50
     elegantly
    0.49
     or
    0.47
    s
    0.47
     Graphics
    0.47
     Compiler
    0.47
     অন্যান্য
    0.46
     etc
    0.45
     drawings
    0.45
    POSITIVE LOGITS
    DEPENDENCIA
    0.61
    ጢ
    0.57
     жить
    0.55
     daarom
    0.53
    IONS
    0.53
     తాగ
    0.52
    URNS
    0.51
    latego
    0.50
    PHIA
    0.50
    眥
    0.50
    Activations Density 0.001%

    No Known Activations