© 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. 48453
    Prev
    Next
    INDEX
    Explanations

    USAGE: or to you

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

    The neuron fires on uppercase section headings or labels (like “USAGE”) often in code or comment blocks.

    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
    physis
    -0.72
     monica
    -0.71
    Vak
    -0.70
    crizione
    -0.69
    Show
    -0.69
    propagate
    -0.69
     relève
    -0.69
    Armor
    -0.69
     considéré
    -0.68
    Од
    -0.68
    POSITIVE LOGITS
    場所に
    0.73
     &$
    0.66
     посту
    0.65
     maps
    0.64
     дире
    0.61
     totals
    0.60
    লি
    0.60
     {},
    0.60
    antis
    0.59
    camara
    0.59
    Activations Density 0.112%

    No Known Activations