© 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. 22-GEMMASCOPE-RES-131K
    7. 66851
    Prev
    Next
    INDEX
    Explanations

    Dominick, into play, as Chelsea, milk

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

    The neuron selectively activates on numeric expressions—years, quantities, statistics, and other digit‐based measurements.

    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
    Переваги
    -0.89
    Currently
    -0.87
    eking
    -0.83
     unborn
    -0.82
    untura
    -0.79
     dinosaurio
    -0.79
     futuristic
    -0.78
     polled
    -0.78
    Kann
    -0.77
     unduly
    -0.77
    POSITIVE LOGITS
     now
    1.43
     теперь
    0.92
     after
    0.90
     once
    0.87
     ahora
    0.85
     since
    0.83
     familiar
    0.82
     generale
    0.82
     when
    0.82
     Now
    0.79
    Activations Density 0.119%

    No Known Activations