© 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. 11945
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to isolated alphanumeric or uppercase‐heavy tokens—e.g. numbers, acronyms, model names or other technical identifiers.

    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
    enne
    0.84
    Magazine
    0.81
    الله
    0.80
    (?:
    0.80
    once
    0.79
    old
    0.79
    Manchester
    0.79
    Allah
    0.79
    কাতার
    0.78
    '
    0.78
    POSITIVE LOGITS
     одном
    0.88
     ingenious
    0.84
     iterative
    0.82
     Divisions
    0.82
     eagerness
    0.80
     amiable
    0.79
     some
    0.78
     impersonal
    0.78
     enterprising
    0.77
     innovative
    0.77
    Activations Density 0.000%

    No Known Activations