© 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. 22-GEMMASCOPE-RES-131K
    4. 36519
    Prev
    Next
    INDEX
    Explanations

    providing reasons

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

    The neuron detects first‐person declarations or personal preference statements (sentences starting with “I” expressing desires, likes, or intentions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    madeus
    -1.05
    Jereo
    -0.94
    ❛
    -0.93
    struzioni
    -0.92
    സ്
    -0.91
     добавил
    -0.89
    ktır
    -0.88
     добра
    -0.85
    Unisex
    -0.85
     Tampoco
    -0.85
    POSITIVE LOGITS
     because
    1.73
     karena
    1.25
     ponieważ
    1.18
     porque
    1.12
     vì
    1.10
     protože
    1.00
     lembrar
    0.98
    porque
    0.96
     mostly
    0.95
     çünkü
    0.94
    Activations Density 0.038%

    No Known Activations