© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5957
    Prev
    Next
    INDEX
    Explanations

    draw after 3

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

    This neuron responds to rare, content-specific tokens (e.g. unusual proper names or low-frequency 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
    حياته
    0.88
    வடிக்க
    0.87
    ف
    0.84
     détermine
    0.83
    ্পর্শ
    0.83
    ＰＥ
    0.82
     을
    0.81
     elenc
    0.81
    Ｚ
    0.80
     lengthen
    0.79
    POSITIVE LOGITS
    ś
    0.89
    ń
    0.76
    吒
    0.66
     terminus
    0.66
    ,
    0.65
     centerpiece
    0.64
    ken
    0.64
     appendage
    0.63
     blueprint
    0.63
     breakup
    0.62
    Activations Density 0.001%

    No Known Activations