© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146215
    Prev
    Next
    INDEX
    Explanations

    ResearchGate publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magnificent
    0.75
     UPC
    0.74
    衫
    0.71
    arendra
    0.71
    ﻱ
    0.67
     odds
    0.65
     neat
    0.65
     USDC
    0.65
    谿
    0.65
     lanc
    0.64
    POSITIVE LOGITS
    }]},
    0.70
    µ
    0.67
    콘
    0.66
     Khe
    0.63
     Kiến
    0.63
     displaystyle
    0.63
     yıldır
    0.62
     Kudos
    0.62
    ָ
    0.62
     জান
    0.61
    Activations Density 0.003%

    No Known Activations