© 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. 22-GEMMASCOPE-RES-131K
    7. 33319
    Prev
    Next
    INDEX
    Explanations

    European shoe sizes

    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_22/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
    鹈
    -1.03
    饮料
    -0.92
    bitkan
    -0.87
    tamanya
    -0.85
    ührung
    -0.82
    atzes
    -0.81
    toMatch
    -0.80
     variantes
    -0.80
     tribus
    -0.80
    𝕿
    -0.79
    POSITIVE LOGITS
    >(</
    0.95
     mueble
    0.88
     normalerweise
    0.85
     sentirse
    0.84
     :/
    0.81
     relacionada
    0.81
    чника
    0.81
     ROCKS
    0.79
    cı
    0.79
    hey
    0.79
    Activations Density 0.002%

    No Known Activations