© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12037
    Prev
    Next
    INDEX
    Explanations

    USD currency amounts

    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
     või
    -1.90
    觊
    -1.84
     Detalles
    -1.84
     or
    -1.73
     that
    -1.73
     scherm
    -1.70
    mathrm
    -1.65
     voordat
    -1.60
    曾經
    -1.52
     geluk
    -1.52
    POSITIVE LOGITS
     limpo
    1.72
    7
    1.70
    cedores
    1.60
     agricultura
    1.52
    都在
    1.52
    𓐍
    1.51
    providedIn
    1.51
    enablog
    1.50
     bringen
    1.47
     всех
    1.46
    Activations Density 0.057%

    No Known Activations