© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93067
    Prev
    Next
    INDEX
    Explanations

    UI elements and code structure

    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
    fullWidth
    -0.98
    往
    -0.95
    案
    -0.88
     Uhr
    -0.87
    惠
    -0.86
     идея
    -0.85
    となり
    -0.84
     lievito
    -0.83
    <tfoot>
    -0.82
    ecera
    -0.82
    POSITIVE LOGITS
     each
    1.47
     princesas
    1.12
    Each
    1.10
     piccoli
    1.06
     randomly
    1.05
     pequeños
    1.02
     adiós
    1.02
     pequeñas
    1.01
     Entscheidungen
    0.98
    vió
    0.96
    Activations Density 0.024%

    No Known Activations