© 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. 11349
    Prev
    Next
    INDEX
    Explanations

    punctuation and code markers

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

    The neuron fires strongly on the “phot” substring, i.e. words related to photography.

    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
     및
    0.74
     új
    0.68
     یا
    0.68
     или
    0.67
     dieci
    0.67
     ও
    0.64
     và
    0.64
     या
    0.64
     и
    0.64
     về
    0.64
    POSITIVE LOGITS
    Descriptions
    0.63
     nachdem
    0.59
     বিশ্বাসঘাত
    0.59
    ெல்லாம்
    0.58
     ardından
    0.57
    osphere
    0.55
    Orbit
    0.54
    Radians
    0.54
    ospheric
    0.53
    criptions
    0.52
    Activations Density 0.000%

    No Known Activations