© 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. 93487
    Prev
    Next
    INDEX
    Explanations

    field trips and excursions

    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
    licitations
    -0.77
     alo
    -0.77
    ulum
    -0.76
    டுத்த
    -0.76
     Alo
    -0.73
    EditPart
    -0.70
    комиться
    -0.70
    ladimir
    -0.69
     alimentos
    -0.69
    質な
    -0.69
    POSITIVE LOGITS
     excursion
    3.16
     excursions
    3.14
     trips
    2.88
     outings
    2.59
     outing
    2.59
     trip
    2.47
    trips
    2.22
     экскур
    2.22
     excur
    2.14
     Excursion
    2.14
    Activations Density 0.026%

    No Known Activations