© 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. 162030
    Prev
    Next
    INDEX
    Explanations

    discuss interface, diseases resulting, potential projects

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

    concerns and sustainability

    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
    恆
    0.57
    誊
    0.55
    恒
    0.54
    隸
    0.47
    偌
    0.45
     Objetivo
    0.44
     ESA
    0.44
    卷
    0.43
    েশ
    0.43
    يريا
    0.43
    POSITIVE LOGITS
     establishes
    0.47
     ascribed
    0.47
    üdis
    0.47
     negoti
    0.45
    িয়াছিলেন
    0.43
    についても
    0.42
    isine
    0.42
     représ
    0.42
     subsidy
    0.42
     embodied
    0.42
    Activations Density 0.001%

    No Known Activations