© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7121
    Prev
    Next
    INDEX
    Explanations

    cognitive therapy and development

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

    The neuron strongly activates on capitalized names, titles, technical terms, and acronyms.

    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
     Namur
    -0.76
    ယ
    -0.70
    Bisous
    -0.69
     imposter
    -0.68
    PTION
    -0.67
     Luxemburg
    -0.67
    չ
    -0.66
     тря
    -0.66
    Rang
    -0.65
    mico
    -0.65
    POSITIVE LOGITS
    junk
    0.81
     PROGRAMME
    0.79
     warna
    0.78
     Ir
    0.78
    preference
    0.77
     bilan
    0.77
    Ls
    0.75
     INDIC
    0.75
     Color
    0.75
    ®
    0.75
    Activations Density 0.037%

    No Known Activations