© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6331
    Prev
    Next
    INDEX
    Explanations

    overall plan categories

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

    The neuron is a “rare‐word detector”—it lights up on infrequent, content‐bearing tokens rather than common function words.

    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
    ége
    0.81
     použit
    0.81
     Ủy
    0.80
    enite
    0.79
    ènes
    0.77
    ient
    0.76
    
    0.75
    osť
    0.74
    ות
    0.73
    ه‌
    0.73
    POSITIVE LOGITS
     größere
    0.85
    新規
    0.84
    τισ
    0.77
    此之外
    0.75
     caseload
    0.73
    샬
    0.73
     срок
    0.73
     zentrale
    0.73
     क्रिस
    0.73
    ी
    0.72
    Activations Density 0.000%

    No Known Activations