© 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. 74892
    Prev
    Next
    INDEX
    Explanations

    mature forms

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

    The neuron activates for the word "mature" when it refers to developmental stages in biological contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is keyed to occurences of terms marking developmental maturity—most prominently the adjective “mature.”

    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
    titial
    -1.95
    螃
    -1.86
    轳
    -1.85
     donnent
    -1.84
     algumas
    -1.83
    
    -1.82
    
    -1.77
     estavam
    -1.76
     使っ
    -1.74
     fizeram
    -1.73
    POSITIVE LOGITS
    In
    2.77
    When
    2.52
    If
    2.50
    During
    2.38
    Other
    2.33
    Another
    2.30
    With
    2.27
    The
    2.25
    Only
    2.19
    There
    2.17
    Activations Density 0.026%

    No Known Activations