© 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. 14991
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions

    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
    ṕ
    -1.04
    Koordinaten
    -1.03
     envie
    -0.99
    Ikr
    -0.99
    aterin
    -0.98
    Moscow
    -0.97
     fue
    -0.95
    ymax
    -0.95
     stroom
    -0.94
     änd
    -0.94
    POSITIVE LOGITS
    2
    0.94
    هور
    0.93
    begin
    0.92
    9
    0.91
    1
    0.88
     periodi
    0.86
    Ventas
    0.85
    ricts
    0.85
     intru
    0.84
    画像は
    0.83
    Activations Density 0.003%

    No Known Activations