© 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. 41758
    Prev
    Next
    INDEX
    Explanations

    Slavic languages and names

    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
     a
    -2.45
    逦
    -2.42
     traducir
    -2.03
     soorten
    -1.91
     extranjera
    -1.91
     They
    -1.90
     encarga
    -1.88
    dată
    -1.86
     Juifs
    -1.81
     peně
    -1.81
    POSITIVE LOGITS
    O
    2.61
    the
    2.36
    耵
    2.13
    its
    2.03
     et
    2.03
    ("
    2.03
     hvor
    2.03
    et
    2.02
    m
    2.02
    2
    1.91
    Activations Density 0.010%

    No Known Activations