© 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. 43514
    Prev
    Next
    INDEX
    Explanations

    descriptive places or concepts

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

    significant number, half day leave

    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
     stric
    0.46
    否定
    0.46
    麿
    0.46
    ців
    0.45
     procent
    0.44
     dici
    0.43
    t
    0.43
     trypt
    0.42
     Layton
    0.42
     स्पष्ट
    0.41
    POSITIVE LOGITS
     χα
    0.44
     forfeited
    0.44
     ट्रॉपिकल
    0.44
     treacher
    0.43
    {\$
    0.43
     chamar
    0.42
     chamada
    0.42
     पाप
    0.41
     hauled
    0.41
     bleached
    0.41
    Activations Density 0.000%

    No Known Activations