© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5801
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis then axis or label

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

    The neuron activates on numeric values and numeric parameter settings in procedural or API‐style text.

    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
    setProperty
    0.56
    getAttribute
    0.55
    toString
    0.52
    定期
    0.52
     प्रोडक्शन
    0.52
    恕
    0.52
     accompanied
    0.52
     formatDate
    0.52
     APPEND
    0.51
    addGroup
    0.51
    POSITIVE LOGITS
     **
    0.76
    **
    0.71
    **:
    0.71
    (**
    0.67
    **,
    0.67
    **(
    0.67
    :**
    0.66
    )#
    0.64
    وبي
    0.63
    )**
    0.62
    Activations Density 0.008%

    No Known Activations