© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15118
    Prev
    Next
    INDEX
    Explanations

    occurred yet, about, cert, attractive, there can, much, swim across, units

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

    The neuron selectively responds to numeric figures—especially years, data points, and quantities—commonly found in market‐research report titles.

    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
    theless
    0.85
    ʚ
    0.85
    филлер
    0.85
     alab
    0.84
     formaldehyde
    0.79
    Nel
    0.79
    Acetic
    0.78
    originals
    0.77
     ಮಾಹಿತ
    0.77
    Elena
    0.76
    POSITIVE LOGITS
    窺
    0.73
     setError
    0.68
     Commit
    0.64
    收到
    0.64
     shrinking
    0.63
    ੍ਹਾਂ
    0.62
    ي
    0.62
     Petitioner
    0.61
     Claimant
    0.61
     severity
    0.61
    Activations Density 0.001%

    No Known Activations