© 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. 1620
    Prev
    Next
    INDEX
    Explanations

    haiku

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

    The neuron fires on named consumer products—especially drug and cosmetic brand names (e.g. Tylenol, Retinol, Pimms, jojoba).

    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
     jeweil
    0.64
     Règlement
    0.64
    Deposit
    0.63
     TextEditing
    0.58
    籲
    0.56
     dezembro
    0.55
    Predicted
    0.55
    UIntValue
    0.54
     Gefahr
    0.54
    neutrophiles
    0.54
    POSITIVE LOGITS
    y
    0.85
     &
    0.84
    al
    0.77
     and
    0.70
    và
    0.67
    l
    0.67
    el
    0.66
     và
    0.65
    esque
    0.65
    或其他
    0.64
    Activations Density 0.000%

    No Known Activations