© 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. 78572
    Prev
    Next
    INDEX
    Explanations

    long and short descriptors

    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
     Krankenhaus
    -0.71
    وردار
    -0.64
    hdashline
    -0.64
     haupts
    -0.62
     DatePicker
    -0.61
     เน
    -0.60
    triangleq
    -0.60
     دری
    -0.60
     previously
    -0.60
     newly
    -0.59
    POSITIVE LOGITS
     lived
    1.29
    running
    1.09
     running
    1.05
     Lived
    1.04
    form
    1.03
    getLong
    1.02
    RUNNING
    1.00
    Long
    0.97
     form
    0.97
    Running
    0.94
    Activations Density 0.055%

    No Known Activations