© 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. 33985
    Prev
    Next
    INDEX
    Explanations

    variable declaration

    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
     then
    -1.31
     afterwards
    -1.20
     again
    -1.14
     now
    -1.14
    ägg
    -1.13
     only
    -1.11
     still
    -1.09
    todoList
    -1.06
     Wartawan
    -1.00
     Schäfer
    -0.98
    POSITIVE LOGITS
    久し
    1.14
     Einladung
    1.02
     créer
    0.99
     calculer
    0.98
    ごめん
    0.98
     также
    0.95
     gérer
    0.94
    まさかの
    0.94
    appliquer
    0.94
    が見える
    0.93
    Activations Density 0.036%

    No Known Activations