© 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. 238
    Prev
    Next
    INDEX
    Explanations

    a or an followed by a word

    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
    <bos>
    -1.95
    .
    -1.82
     to
    -1.76
    rijving
    -1.70
     anderem
    -1.63
    undidad
    -1.63
     and
    -1.56
    ,\,\
    -1.51
    𝘴
    -1.50
     dahin
    -1.47
    POSITIVE LOGITS
    AS
    1.73
     emballage
    1.66
    込む
    1.54
    ifiers
    1.52
    alians
    1.51
    艫
    1.49
    ナイキ
    1.48
     icona
    1.48
    簓
    1.45
     -
    1.43
    Activations Density 0.341%

    No Known Activations