© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    This neuron primarily detects words that name specific roles, titles, or professions.

    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
     الانسان
    0.63
    มั่น
    0.63
     chúng
    0.62
     scritta
    0.62
    i
    0.60
     মৃত্য
    0.60
    非常的
    0.59
     の
    0.59
    ii
    0.59
     sorgt
    0.59
    POSITIVE LOGITS
    ानुसार
    0.70
    unteer
    0.69
    নার্থ
    0.66
     percentile
    0.64
     quartiers
    0.64
     plabic
    0.63
     Atelier
    0.63
     semicircle
    0.63
     overlap
    0.62
     sideline
    0.62
    Activations Density 0.504%

    No Known Activations