© 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. 117800
    Prev
    Next
    INDEX
    Explanations

    mods, plugins, enhancements

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

    The neuron responds to uppercase acronyms, product or mod names, and other technical identifiers (e.g. LC, PD, FR, ENB).

    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
    VELAND
    -0.86
    類型
    -0.83
    ヴ
    -0.82
    Dès
    -0.81
    かったです
    -0.81
    madamente
    -0.79
    Popover
    -0.79
    pygame
    -0.77
     przód
    -0.77
    initWithFrame
    -0.75
    POSITIVE LOGITS
     Enhanced
    1.20
     Better
    1.10
     improved
    1.08
     Improved
    1.05
    Enhanced
    1.05
     enhanced
    1.04
     mod
    1.03
     better
    1.01
     enhancements
    1.00
    improved
    0.98
    Activations Density 0.054%

    No Known Activations