© 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. 86107
    Prev
    Next
    INDEX
    Explanations

    endocrine/exocrine and recounting events

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

    words or phrases related to recounting or describing accounts of events.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    -3.97
    {
    -3.47
    1
    -3.27
    9
    -2.86
            
    -2.86
     {
    -2.80
    How
    -2.66
    What
    -2.63
    5
    -2.63
    6
    -2.58
    POSITIVE LOGITS
    寕
    3.08
    曏
    2.84
    儅
    2.80
    髎
    2.73
    夲
    2.64
    ᯅ
    2.61
    
    2.61
    孭
    2.59
    铩
    2.58
     ménages
    2.55
    Activations Density 0.002%

    No Known Activations