© 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. 19833
    Prev
    Next
    INDEX
    Explanations

    world flyweight

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

    compliance and variables

    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
     терито
    0.54
    ë
    0.50
     ভালো
    0.49
    湿度
    0.47
    ė
    0.46
     Blüten
    0.45
     основ
    0.44
     بغیر
    0.44
    ër
    0.44
    estabelecimento
    0.43
    POSITIVE LOGITS
     amts
    0.48
     automat
    0.47
    J
    0.46
     avons
    0.43
     Programming
    0.43
     angl
    0.43
     --
    0.43
     erne
    0.42
     &
    0.42
     formats
    0.41
    Activations Density 0.000%

    No Known Activations