© 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. 33715
    Prev
    Next
    INDEX
    Explanations

    method calls ending in parentheses

    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
    が
    -1.46
    を
    -1.16
     tulum
    -1.15
    「
    -1.13
     embre
    -1.13
     hecta
    -1.11
     divertimento
    -1.07
     gila
    -1.07
     abnorm
    -1.05
     ⭐
    -1.04
    POSITIVE LOGITS
    なのでしょう
    1.15
    ものに
    1.11
     tiež
    1.01
    ambig
    1.01
    殃
    1.00
     emel
    0.96
    قامت
    0.96
    ronyms
    0.95
     comiendo
    0.94
     Übersicht
    0.94
    Activations Density 0.018%

    No Known Activations