© 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. 13313
    Prev
    Next
    INDEX
    Explanations

    ever- increasing

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

    This neuron fires on the hyphenated phrase “ever – increasing” (i.e. the sequence “ever-increasing”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    瘣
    -2.73
    喑
    -2.58
    
    -2.52
     beiden
    -2.42
    
    -2.34
    ⢪
    -2.31
    筇
    -2.30
    
    -2.28
    
    -2.27
    곗
    -2.27
    POSITIVE LOGITS
    There
    2.52
    The
    2.50
     have
    2.47
    there
    2.30
    ):
    2.17
    This
    2.16
    We
    2.16
    They
    2.16
     in
    2.11
     Not
    2.08
    Activations Density 0.005%

    No Known Activations