© 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. 34-GEMMASCOPE-RES-131K
    7. 31475
    Prev
    Next
    INDEX
    Explanations

    come or comes

    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_34/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
    escent
    -0.92
    leiter
    -0.87
    heten
    -0.81
    GetAxis
    -0.80
    ('.');
    -0.80
     входа
    -0.80
    umpang
    -0.77
     perjalanan
    -0.76
    ñales
    -0.75
     cerdo
    -0.74
    POSITIVE LOGITS
     come
    2.56
     comes
    2.52
     came
    2.42
    Come
    1.89
     Come
    1.73
    Came
    1.69
    Comes
    1.64
    come
    1.60
    COME
    1.59
     Comes
    1.48
    Activations Density 0.018%

    No Known Activations