© 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. 77821
    Prev
    Next
    INDEX
    Explanations

    version control systems

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires primarily on software/technology names (especially KDE-related components) and their accompanying version or numeric identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     selfie
    -1.14
    https
    -1.00
     emoji
    -0.99
     relatable
    -0.97
    \,.
    -0.95
    upyter
    -0.94
     полиции
    -0.94
     Tumblr
    -0.89
     microbiome
    -0.89
     idk
    -0.88
    POSITIVE LOGITS
     CVS
    1.05
    CVS
    0.99
    toaster
    0.95
     Nets
    0.87
     Cooker
    0.84
     Hobbes
    0.84
     Distributions
    0.84
    bánh
    0.83
    "/",
    0.83
    sourceforge
    0.83
    Activations Density 0.412%

    No Known Activations