© 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-16K
    7. 11679
    Prev
    Next
    INDEX
    Explanations

    exactly what/how/the

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

    exactness

    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_16k_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
     മാത്രം
    0.74
     ای
    0.68
    基本的に
    0.66
    ደበ
    0.62
    utilisateur
    0.62
     essais
    0.62
    ॉड
    0.61
    )[
    0.61
    ciones
    0.60
    勧
    0.58
    POSITIVE LOGITS
    exactly
    1.09
     EXACT
    0.97
    exact
    0.93
     exactly
    0.92
     dokładnie
    0.91
    Exact
    0.87
     Exactly
    0.86
    Exactly
    0.86
     точно
    0.85
     exacta
    0.82
    Activations Density 0.263%

    No Known Activations