© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47932
    Prev
    Next
    INDEX
    Explanations

    URLs and separators

    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
    hoven
    -0.86
     Stop
    -0.84
     Making
    -0.82
     Latina
    -0.81
     STOP
    -0.81
     Experiment
    -0.80
     Purpose
    -0.79
    URERS
    -0.78
     Survey
    -0.77
     Makes
    -0.75
    POSITIVE LOGITS
    Notation
    0.85
     dismal
    0.84
    Typo
    0.83
    Ais
    0.82
    QY
    0.81
    fores
    0.81
     malades
    0.78
    NIK
    0.78
    Astronomy
    0.77
    Quinta
    0.77
    Activations Density 0.000%

    No Known Activations