© 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. 20331
    Prev
    Next
    INDEX
    Explanations

    examples and definitions

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

    example, inizio, start

    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
    <unused532>
    0.51
     भले
    0.49
     प्रीवियस
    0.45
    äuser
    0.45
    㳒
    0.45
    <unused1653>
    0.44
    <unused266>
    0.43
    generalized
    0.43
     गंभीर
    0.43
    archiwizowane
    0.43
    POSITIVE LOGITS
     Example
    0.54
     section
    0.52
     example
    0.49
    为例
    0.48
     icon
    0.48
    :
    0.47
     ejemplo
    0.46
     Symbol
    0.45
     Section
    0.45
     exemplo
    0.45
    Activations Density 0.072%

    No Known Activations