© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15605
    Prev
    Next
    INDEX
    Explanations

    pros and cons

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

    The neuron fires strongly on tokens bearing common English derivational suffixes (‐ing, ‐ly, ‐er, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hague
    0.80
     Controlling
    0.77
     Scope
    0.74
     Hurst
    0.74
    瑙
    0.73
     আরি
    0.72
     Expenditure
    0.71
     कामयाब
    0.71
    内在
    0.71
     Increased
    0.70
    POSITIVE LOGITS
    nextNode
    0.83
    ﻢ
    0.80
    tomorrow
    0.76
    gameOver
    0.75
    middlewares
    0.74
    に対し
    0.73
     ambas
    0.73
    次回
    0.73
    s
    0.73
     pequenas
    0.73
    Activations Density 0.002%

    No Known Activations