© 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. 12924
    Prev
    Next
    INDEX
    Explanations

    website paths and links

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

    The neuron picks out section or article headlines—lines written in title‐style capitalization (e.g. standalone headers).

    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
    dsale
    0.73
    ۔
    0.72
    。...
    0.71
    dje
    0.69
    ління
    0.68
     אשר
    0.68
     которы
    0.68
    。。
    0.68
    .。
    0.68
     которого
    0.67
    POSITIVE LOGITS
    ↵↵
    0.96
     Welcome
    0.80
     At
    0.76
     After
    0.76
     This
    0.73
     [
    0.73
     What
    0.73
     Finally
    0.73
     First
    0.72
     We
    0.71
    Activations Density 0.209%

    No Known Activations