© 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. 63257
    Prev
    Next
    INDEX
    Explanations

    technology services and enterprise development

    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
    Vielleicht
    -1.02
    Wird
    -1.00
    所得
    -0.95
    Gibt
    -0.94
     developer
    -0.90
    otations
    -0.89
    Natürlich
    -0.88
    Genau
    -0.86
    Fragen
    -0.85
    Samstag
    -0.84
    POSITIVE LOGITS
    transmitter
    0.79
     disruptions
    0.79
     workmen
    0.79
    vrigt
    0.77
     mf
    0.76
    |(
    0.75
    radial
    0.75
     BFS
    0.75
     visualized
    0.75
     grunn
    0.74
    Activations Density 0.019%

    No Known Activations