© 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. 7705
    Prev
    Next
    INDEX
    Explanations

    although followed by verbs

    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
     is
    -1.77
    ("")]
    -1.77
    </b>
    -1.65
    不仅仅
    -1.60
     求人
    -1.51
    viembre
    -1.49
    这般
    -1.48
    ar
    -1.48
     exemplifies
    -1.41
    此外
    -1.41
    POSITIVE LOGITS
     angeschlossen
    1.90
     bedeckt
    1.86
    ordnen
    1.80
     leichte
    1.75
    ！】
    1.73
    橚
    1.73
     gefahren
    1.67
     ersche
    1.67
     και
    1.66
     và
    1.65
    Activations Density 0.054%

    No Known Activations