© 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. 13316
    Prev
    Next
    INDEX
    Explanations

    casual, traditional, atmosphere

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

    The main thing this neuron does is pick out strongly positive descriptive words and phrases expressing favorable evaluations (e.g. “outstanding,” “well-appointed,” “fantastic,” “excellent,” etc.).

    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
     increíble
    1.01
     gracias
    0.96
    めっちゃ
    0.95
     AMAZING
    0.95
     😍
    0.93
     bellissimo
    0.93
     🥰
    0.92
    Gracias
    0.90
     🙌
    0.90
    🤩
    0.90
    POSITIVE LOGITS
    未必
    0.65
     popularized
    0.61
     postulated
    0.58
     pojav
    0.57
     dichotomy
    0.56
    用い
    0.56
     auteur
    0.55
    DBMS
    0.55
     "*.
    0.55
     evanescent
    0.55
    Activations Density 0.051%

    No Known Activations