© 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. 224184
    Prev
    Next
    INDEX
    Explanations

    after Guide

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

    different objects or concepts

    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
    decimals
    0.54
    น
    0.49
     بڑی
    0.48
    פ
    0.46
    ด้
    0.46
    ཛ
    0.45
    assurer
    0.45
    ശ
    0.44
    GRect
    0.44
    ੨
    0.43
    POSITIVE LOGITS
     chris
    0.53
     Chris
    0.49
     Familie
    0.47
    രണ
    0.46
     Conor
    0.45
     Rajput
    0.44
     Manish
    0.44
     archery
    0.44
     Erik
    0.44
     koncept
    0.44
    Activations Density 0.001%

    No Known Activations