© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11355
    Prev
    Next
    INDEX
    Explanations

    align with

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

    The neuron strongly activates on individual capitalized tokens—i.e. proper names and other non‐sentence–initial words that begin with an uppercase letter.

    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_31_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
    चुरल
    0.63
    TRAS
    0.59
     overwhelmingly
    0.58
    archical
    0.57
     LOADING
    0.57
     aquellos
    0.56
    анг
    0.56
    ့
    0.56
     어떤
    0.55
     aquellas
    0.55
    POSITIVE LOGITS
    querque
    0.63
    ernate
    0.59
    geç
    0.55
     सुबह
    0.54
    Breaking
    0.52
     yht
    0.52
    ígen
    0.51
    सुबह
    0.51
    ⬆
    0.50
     phosphatase
    0.50
    Activations Density 0.238%

    No Known Activations