© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11967
    Prev
    Next
    INDEX
    Explanations

    Args: documentation parameter

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

    The neuron strongly fires on numeric tokens—especially measurements, quantities, or floating-point numbers—marking places where specs or numerical values appear.

    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_31_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
     தன்னை
    0.60
    keydown
    0.58
    linecap
    0.57
    心脏
    0.55
     kwest
    0.54
     而
    0.54
     கிர
    0.53
    儘
    0.52
     इच्छा
    0.52
     hér
    0.52
    POSITIVE LOGITS
     df
    0.59
    enic
    0.58
     linestyle
    0.55
    <start_of_image>
    0.54
     Baths
    0.52
    ↵↵
    0.51
    Is
    0.51
    Ψ
    0.51
     traz
    0.50
    ψ
    0.50
    Activations Density 0.004%

    No Known Activations