© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38903
    Prev
    Next
    INDEX
    Explanations

    nationwide, statewide, national, wide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Etimología
    -1.64
    ARROLLO
    -1.43
     Comprometido
    -1.40
    
    -1.38
    bufio
    -1.38
    なども
    -1.34
     няколко
    -1.32
     Obtén
    -1.29
    ᯅ
    -1.28
     langkah
    -1.27
    POSITIVE LOGITS
    c
    1.65
    p
    1.59
    f
    1.58
     impulsar
    1.34
    with
    1.30
    as
    1.30
    i
    1.29
    /
    1.25
    (
    1.25
    in
    1.25
    Activations Density 0.095%

    No Known Activations