© 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. 103551
    Prev
    Next
    INDEX
    Explanations

    retrieve or collect

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

    This neuron consistently lights up on extended descriptive or expository passages—that is, on sequences of content‐heavy, “technique or product” style writing rather than narrative or dialogue.

    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
    Processes
    -0.82
     السياس
    -0.82
    द्
    -0.82
    Temper
    -0.82
     شخصية
    -0.79
    raltar
    -0.79
    ุณ
    -0.79
    renal
    -0.78
     Prisma
    -0.77
    stretched
    -0.76
    POSITIVE LOGITS
     retrieve
    1.27
     retrieved
    1.12
     retrieving
    1.05
    retrieve
    0.91
     bites
    0.88
    回収
    0.86
     animating
    0.84
     enticing
    0.83
     Retrieve
    0.82
     retrieves
    0.82
    Activations Density 0.004%

    No Known Activations