© 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. 34-GEMMASCOPE-RES-131K
    7. 93112
    Prev
    Next
    INDEX
    Explanations

    information regarding

    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_34/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
    linawan
    -1.16
     Вя
    -1.09
     ingenuity
    -1.08
     δημιουργ
    -1.08
    大幅
    -1.07
    火力
    -1.06
    ibig
    -1.05
     marvelous
    -1.03
     Татьяна
    -1.00
     echte
    -0.98
    POSITIVE LOGITS
     about
    2.22
     regarding
    1.66
     gathered
    1.55
    .
    1.34
    ymmetry
    1.27
     available
    1.27
     contained
    1.26
    ally
    1.26
     gathering
    1.25
     provided
    1.23
    Activations Density 0.049%

    No Known Activations