© 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. 10-GEMMASCOPE-RES-131K
    7. 129513
    Prev
    Next
    INDEX
    Explanations

    .type and definitions

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

    The neuron fires most strongly on unusual or infrequent tokens (whether special symbols, rare words, or uncommon technical terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ৄ
    -2.03
    𓆝
    -1.99
    觏
    -1.96
     delightfully
    -1.90
    罣
    -1.88
    entrevista
    -1.83
    fought
    -1.82
    
    -1.81
    inerario
    -1.78
     hlavy
    -1.77
    POSITIVE LOGITS
     while
    2.19
     because
    2.08
    //
    1.96
     there
    1.95
     has
    1.91
    after
    1.91
     gives
    1.77
     every
    1.77
     so
    1.77
     it
    1.71
    Activations Density 0.076%

    No Known Activations