© 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. 216658
    Prev
    Next
    INDEX
    Explanations

    intent or meaning

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

    mean to / clarify meaning

    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
    a
    0.93
    in
    0.72
    n
    0.69
    am
    0.66
    nicht
    0.65
    m
    0.65
    name
    0.64
    p
    0.64
    b
    0.63
    um
    0.62
    POSITIVE LOGITS
     tek
    0.63
    פה
    0.58
    esk
    0.54
     이에
    0.52
    的同时
    0.50
    ester
    0.49
    子公司
    0.49
     sillä
    0.48
    اتر
    0.47
     causative
    0.47
    Activations Density 0.016%

    No Known Activations