© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130809
    Prev
    Next
    INDEX
    Explanations

    programming constructs and technical terms

    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
    abilir
    -1.00
    uksia
    -0.99
    jadwal
    -0.97
     autorización
    -0.97
    ötä
    -0.90
    DATOS
    -0.90
     épreuve
    -0.89
     nová
    -0.88
     préparer
    -0.88
     CÁ
    -0.87
    POSITIVE LOGITS
     another
    0.93
    le
    0.91
     continued
    0.89
    </h5>
    0.88
     If
    0.85
     This
    0.84
    !--
    0.84
    dafx
    0.81
     ещё
    0.80
     ,.
    0.80
    Activations Density 0.017%

    No Known Activations