© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32716
    Prev
    Next
    INDEX
    Explanations

    registration process and fees

    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
    жки
    -0.84
    factor
    -0.83
    кож
    -0.81
     tū
    -0.80
    diu
    -0.80
    geti
    -0.79
    Grass
    -0.78
    leding
    -0.78
    GRASS
    -0.77
    grass
    -0.77
    POSITIVE LOGITS
     process
    1.83
     fee
    1.55
     fees
    1.44
     procedures
    1.27
     procedure
    1.27
     requirements
    1.19
     form
    1.18
     information
    1.17
     requirement
    1.15
     processes
    1.13
    Activations Density 0.041%

    No Known Activations