© 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. 57607
    Prev
    Next
    INDEX
    Explanations

    ocean frontage

    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
     Crossing
    -0.78
    ítás
    -0.77
     Fur
    -0.73
    НК
    -0.71
    regierung
    -0.71
     região
    -0.68
     reflexión
    -0.68
    谲
    -0.68
    zamos
    -0.66
     Flooring
    -0.66
    POSITIVE LOGITS
     frontage
    3.55
    fron
    2.25
     fron
    2.17
     Fron
    2.09
    Fron
    2.03
    front
    1.95
     front
    1.95
     fronts
    1.91
    FRONT
    1.69
     FRONT
    1.55
    Activations Density 0.017%

    No Known Activations