© 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. 34100
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and symbols

    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
     such
    -0.99
     likely
    -0.93
     probably
    -0.90
     presumably
    -0.88
     same
    -0.87
    hamdulillah
    -0.83
     all
    -0.81
     indicated
    -0.81
     selected
    -0.81
     either
    -0.81
    POSITIVE LOGITS
    тическое
    0.98
     מים
    0.93
     برای
    0.91
    AccessFile
    0.89
     Bavarian
    0.88
     Commer
    0.87
    endency
    0.85
    而已
    0.85
    父亲
    0.85
    bigliamento
    0.84
    Activations Density 0.039%

    No Known Activations