© 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. 3301
    Prev
    Next
    INDEX
    Explanations

    object creation and calling methods

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

    The neuron strongly activates on single‐letter identifiers (e.g. “m”, “r”, “t”) used as aliases in code or queries.

    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
     لهذه
    0.73
     diese
    0.69
     नसते
    0.63
    THR
    0.62
     dieser
    0.62
    ^
    0.62
     thofe
    0.61
    نګه
    0.59
     these
    0.59
     Plough
    0.59
    POSITIVE LOGITS
    扆
    0.69
     également
    0.59
     اپنی
    0.58
     دارای
    0.57
     ने
    0.56
     अपनी
    0.56
     தலைமையில்
    0.55
    getRequest
    0.55
     दिखाई
    0.55
     début
    0.54
    Activations Density 0.000%

    No Known Activations