© 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. 63111
    Prev
    Next
    INDEX
    Explanations

    code and documentation structure

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

    The neuron fires most strongly on tokens that serve as section headers or labels (e.g. “Description,” “Related,” “template,” “Dependency,” or other standalone heading-style words).

    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
    Мир
    -0.94
     hű
    -0.87
     perdon
    -0.85
     virke
    -0.85
     euró
    -0.85
    🕑
    -0.83
    %%%%%%%%%%
    -0.82
    sträger
    -0.81
    RECEIVE
    -0.81
    ésultat
    -0.81
    POSITIVE LOGITS
     Established
    0.75
     größte
    0.73
     here
    0.73
     przedstaw
    0.73
    EST
    0.72
     собира
    0.71
    aksanaan
    0.71
     Dolores
    0.71
     falsche
    0.71
     좋아
    0.70
    Activations Density 0.001%

    No Known Activations