© 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. 189852
    Prev
    Next
    INDEX
    Explanations

    easy, display, complement

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

    purchase path

    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
    熠
    0.44
     coupler
    0.44
     என்றால்
    0.43
     اللَّ
    0.42
    لا
    0.42
     couplers
    0.42
     handlebars
    0.41
    UISE
    0.39
     chilli
    0.39
     ripples
    0.39
    POSITIVE LOGITS
    dmg
    0.45
     संपत्ति
    0.44
    endenza
    0.44
     fortemente
    0.44
    ∟
    0.42
    ્સ
    0.42
     फंक्शन
    0.42
    pson
    0.42
    masında
    0.41
     তৈ
    0.41
    Activations Density 0.001%

    No Known Activations