© 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. 5417
    Prev
    Next
    INDEX
    Explanations

    input type attributes

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

    The neuron spikes on HTML hyperlink attributes and link-related tokens (e.g. href, rel, bookmark).

    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
     sprang
    0.64
     κ
    0.58
     博
    0.58
    டித்த
    0.55
     Bootstrap
    0.55
    டைந்த
    0.55
    بوت
    0.54
    ɧ
    0.54
     六
    0.53
     الداخلية
    0.51
    POSITIVE LOGITS
    checkbox
    0.65
    hidden
    0.59
    ritto
    0.58
    tel
    0.57
    ankton
    0.57
    abdomen
    0.55
    ంచి
    0.54
    évaluation
    0.54
    udsman
    0.54
    texas
    0.53
    Activations Density 0.026%

    No Known Activations