© 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. 10-GEMMASCOPE-RES-131K
    7. 1706
    Prev
    Next
    INDEX
    Explanations

    wipe, dry, erase

    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_10/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
    (
    -3.25
    \
    -3.14
    A
    -2.56
     –
    -2.39
     
    -2.38
    E
    -2.36
    >
    -2.34
    s
    -2.33
    Y
    -2.31
    </h2>
    -2.30
    POSITIVE LOGITS
    搋
    2.36
    鱨
    2.05
    Wady
    2.02
    Berat
    2.02
    Mitar
    2.02
    虓
    1.99
    鶺
    1.98
    ارتمان
    1.98
    decoración
    1.95
    Waga
    1.95
    Activations Density 0.007%

    No Known Activations