© 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. 93006
    Prev
    Next
    INDEX
    Explanations

    railway infrastructure and locations

    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
    prototype
    -0.83
     prototype
    -0.77
    chaub
    -0.74
     Glaze
    -0.74
    جراء
    -0.73
    indir
    -0.71
    Prototype
    -0.69
     realizados
    -0.68
     ragu
    -0.68
     Prototype
    -0.66
    POSITIVE LOGITS
     stalls
    0.85
    ellt
    0.76
    BURGH
    0.75
     Leone
    0.74
    logenetic
    0.71
    accompanied
    0.71
    examined
    0.71
     shoots
    0.70
    lahan
    0.70
    dahl
    0.70
    Activations Density 0.021%

    No Known Activations