© 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. 127951
    Prev
    Next
    INDEX
    Explanations

    nature and outdoors

    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
     for
    -1.70
    biscuit
    -1.42
     Japão
    -1.38
    ntä
    -1.35
    श्यक
    -1.35
    mpagne
    -1.33
     Jahrgang
    -1.30
    hiva
    -1.30
    錚
    -1.25
    uuuu
    -1.23
    POSITIVE LOGITS
    
    1.63
     albeit
    1.57
     surrounding
    1.53
    definitely
    1.51
    ⸨
    1.50
     イラストレーション
    1.49
    袛
    1.45
    ㈲
    1.45
    gendes
    1.45
     rurales
    1.45
    Activations Density 0.024%

    No Known Activations