© 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. 55967
    Prev
    Next
    INDEX
    Explanations

    services and scheduling

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

    dataset descriptions

    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
    measurable
    0.48
    IN
    0.48
    上了
    0.47
    ss
    0.45
    visible
    0.45
    fly
    0.43
    ↵
    0.43
    side
    0.42
    出
    0.42
    support
    0.42
    POSITIVE LOGITS
     artik
    0.55
     artículos
    0.55
     وق
    0.51
     planta
    0.50
     detalles
    0.50
     marcha
    0.50
     газета
    0.50
     خلا
    0.49
     rhubarb
    0.49
     قبض
    0.48
    Activations Density 0.000%

    No Known Activations