© 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. 1819
    Prev
    Next
    INDEX
    Explanations

    followed by common words

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

    The neuron never fires—it produces zero activation on every token and thus doesn’t detect any pattern.

    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
    -
    0.73
    0
    0.69
    _
    0.68
    및
    0.66
    /
    0.62
    =
    0.59
    +
    0.59
    で
    0.59
    '
    0.58
    .
    0.57
    POSITIVE LOGITS
     it
    0.84
     nonostante
    0.80
    それは
    0.75
     there
    0.74
     Admittedly
    0.72
     አይደለም
    0.70
     cilvē
    0.69
    យើង
    0.68
     Despite
    0.68
     Obwohl
    0.68
    Activations Density 0.169%

    No Known Activations