© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4782
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron fires on personal names and other human referents (e.g. character names or kinship terms like “husband”).

    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
     J
    0.78
     P
    0.71
     K
    0.70
     V
    0.68
     O
    0.66
     R
    0.65
     C
    0.64
     Max
    0.62
     S
    0.61
     A
    0.60
    POSITIVE LOGITS
     proporciona
    0.62
     помогает
    0.62
     swoop
    0.61
     সাহায্য
    0.59
     bantuan
    0.59
     transmittance
    0.57
     passende
    0.56
     അവളെ
    0.55
    让她
    0.55
     ją
    0.54
    Activations Density 0.012%

    No Known Activations