© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 390
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens that are personal names (proper first‐name or user‐handle tokens).

    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
    mapStateToProps
    0.31
    FromBody
    0.30
    だけでなく
    0.29
    것
    0.29
    BleStatus
    0.29
    igten
    0.28
    ⥤
    0.28
    えています
    0.28
    [++
    0.28
    purecounter
    0.28
    POSITIVE LOGITS
    y
    0.36
    ana
    0.35
    el
    0.35
    Angela
    0.34
    man
    0.34
    ina
    0.33
    in
    0.33
    INA
    0.33
     Hawk
    0.32
    on
    0.32
    Activations Density 0.000%

    No Known Activations