© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14689
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to broad, inclusive or generalizing terms (e.g. “all,” “more than,” “we”) that signal sweeping statements or coverage.

    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
     .
    0.98
     אבל
    0.82
     But
    0.81
    But
    0.80
    /
    0.77
    ²
    0.77
     。
    0.76
    -
    0.75
    のは
    0.73
    2
    0.73
    POSITIVE LOGITS
     handlebar
    0.89
     inept
    0.82
     intermission
    0.76
    횃
    0.76
     valiant
    0.75
     sentient
    0.75
     सहानु
    0.75
     insidious
    0.74
     inciting
    0.74
    छात्रा
    0.73
    Activations Density 0.001%

    No Known Activations