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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84757
    Prev
    Next
    INDEX
    Explanations

    come with prepositions

    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>
    -2.22
     \_
    -2.08
    medriver
    -2.03
     вашего
    -1.85
    ?"
    -1.85
    ();
    -1.84
    所以在
    -1.81
    (),
    -1.78
    one
    -1.77
     speichern
    -1.77
    POSITIVE LOGITS
     from
    2.09
     Such
    1.65
     Comes
    1.61
    Отзывы
    1.60
     jewish
    1.59
     Coming
    1.58
     lesquelles
    1.55
    韡
    1.55
    promote
    1.55
    autorité
    1.54
    Activations Density 0.098%

    No Known Activations