© 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. 72256
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
     biela
    -1.36
     chaleureux
    -1.35
     épais
    -1.31
     contactez
    -1.30
    மா
    -1.29
    kursi
    -1.28
     conva
    -1.27
     oublié
    -1.27
     Você
    -1.26
    lamabad
    -1.24
    POSITIVE LOGITS
    g
    1.45
     essas
    1.35
     tyto
    1.31
    などを
    1.25
    ional
    1.23
    l
    1.21
    o
    1.21
     heath
    1.16
     to
    1.16
    aw
    1.16
    Activations Density 0.003%

    No Known Activations