© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    of the

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

    This neuron fires on uncommon, content-rich tokens (i.e. rarer or more “technical” words rather than frequent function words).

    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
    Ｇ
    0.53
     SUPER
    0.52
    W
    0.51
     NICE
    0.50
    /
    0.47
     SOA
    0.46
    Ｗ
    0.45
     VERY
    0.44
    D
    0.44
    HIP
    0.44
    POSITIVE LOGITS
     hepatocytes
    0.55
    orylation
    0.54
    aterina
    0.52
     सलूशन
    0.49
    फ्त
    0.46
     忄
    0.45
     intravascular
    0.44
    avati
    0.44
     izra
    0.44
    otransferase
    0.44
    Activations Density 0.003%

    No Known Activations