© 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. 209480
    Prev
    Next
    INDEX
    Explanations

    creation and contribution

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

    maintaining very transparent

    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
    ě
    0.52
    dotnet
    0.46
    淉
    0.45
    态度
    0.45
     वाक्या
    0.45
    强大
    0.44
    itekt
    0.44
    sinya
    0.44
    站
    0.44
    opsy
    0.44
    POSITIVE LOGITS
     consideradas
    0.54
     isActive
    0.50
     polymeric
    0.49
     methylation
    0.48
     gonad
    0.48
     mated
    0.48
    ഥി
    0.48
     lubricating
    0.47
     cannabinoids
    0.46
     owning
    0.46
    Activations Density 0.000%

    No Known Activations