© 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. 34-GEMMASCOPE-RES-131K
    7. 108668
    Prev
    Next
    INDEX
    Explanations

    materials for play and learning

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

    The neuron fires on descriptions or section-title phrases of hands-on sensory play/craft activities (e.g. finger-painting or bubble-wrap play).

    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
     beeswax
    -0.82
     CHF
    -0.81
    Sesion
    -0.78
     Darfur
    -0.75
    记录
    -0.75
    ḱ
    -0.74
     $|\
    -0.73
     herum
    -0.73
     při
    -0.73
     records
    -0.73
    POSITIVE LOGITS
     Elmer
    1.17
    Elmer
    0.98
    gak
    0.81
    готовление
    0.81
     gak
    0.76
    Decoder
    0.75
    uhnya
    0.75
    sentences
    0.73
    issens
    0.72
     食
    0.71
    Activations Density 0.009%

    No Known Activations