© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35093
    Prev
    Next
    INDEX
    Explanations

    initial or preliminary

    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
    пущен
    -0.83
    gruntled
    -0.80
    ulisan
    -0.79
     />
    -0.74
     or
    -0.73
    丁目
    -0.73
     Κυ
    -0.73
     uses
    -0.73
     />\
    -0.73
    elakaan
    -0.71
    POSITIVE LOGITS
     اولیه
    1.73
     preliminary
    1.73
     initially
    1.63
    初步
    1.58
     initial
    1.45
    Preliminary
    1.40
     PRELIM
    1.39
     provisional
    1.37
     inicialmente
    1.36
     Preliminary
    1.35
    Activations Density 0.112%

    No Known Activations