© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7869
    Prev
    Next
    INDEX
    Explanations

    multilingual or technical contexts

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

    The neuron is keyed to the “#” symbol, effectively picking up on hash‐prefixed headings or comment markers.

    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
     неиз
    0.84
    Campe
    0.84
    Conj
    0.82
    Malformed
    0.81
    ν
    0.80
    t
    0.79
    Comic
    0.77
    Slf
    0.77
     día
    0.77
    0.77
    POSITIVE LOGITS
     subscrib
    0.80
    पृथ
    0.80
    కీయ
    0.79
    থিল
    0.78
    啇
    0.77
     amending
    0.76
     accru
    0.76
    ᱕
    0.76
    sunline
    0.75
     koordin
    0.75
    Activations Density 0.001%

    No Known Activations