© 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. 150194
    Prev
    Next
    INDEX
    Explanations

    word followed by specifying word

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

    parenthetical explanations or clarifications

    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
    Script
    0.51
    Scripts
    0.46
    port
    0.45
    Window
    0.43
     perturbed
    0.43
    Feb
    0.42
    window
    0.42
    u
    0.42
    WINDOW
    0.41
    quint
    0.41
    POSITIVE LOGITS
    рики
    0.54
     codef
    0.50
     definiciones
    0.50
    kfollowers
    0.50
    рик
    0.49
     тү
    0.49
     satisfactor
    0.48
     abar
    0.48
     afară
    0.48
     duas
    0.47
    Activations Density 0.000%

    No Known Activations