© 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. 113646
    Prev
    Next
    INDEX
    Explanations

    place names followed by entities

    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
    The
    -1.99
    ⃚
    -1.70
    铩
    -1.70
    When
    -1.70
     якщо
    -1.68
    voyez
    -1.67
    Tanto
    -1.65
     borsa
    -1.63
    Another
    -1.61
     Another
    -1.59
    POSITIVE LOGITS
    '
    1.79
     oth
    1.77
    などは
    1.54
    ’
    1.53
    了很多
    1.49
     spp
    1.48
    s
    1.47
    聞いた
    1.43
    などに
    1.43
    使って
    1.42
    Activations Density 0.009%

    No Known Activations