© 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. 15453
    Prev
    Next
    INDEX
    Explanations

    between a, between some, max_val, his special, span some, via job, thoughts a

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

    The neuron fires on common function words—particularly second‐person pronouns and short articles (e.g. “you,” “are,” “a”).

    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
    품
    0.76
     froid
    0.74
    stricken
    0.71
    ١
    0.69
    피
    0.68
    ১
    0.66
    동안
    0.64
    قطع
    0.64
    quilla
    0.63
    프
    0.63
    POSITIVE LOGITS
     Также
    0.92
     понимают
    0.88
     agonists
    0.86
     viaje
    0.83
     электро
    0.83
     horoscope
    0.82
    zantine
    0.82
     Perfectly
    0.81
     главной
    0.81
    urow
    0.80
    Activations Density 0.001%

    No Known Activations