© 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. 6504
    Prev
    Next
    INDEX
    Explanations

    usernames with numbers or identifiers

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

    The neuron strongly activates on tokens that are parts of forum usernames or user handles.

    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
     Kollegen
    0.39
     інформа
    0.38
     bisschen
    0.37
     Schönheit
    0.35
    firmasi
    0.34
    alakip
    0.34
    딪
    0.34
    𝑪
    0.34
     Physik
    0.33
    みんな
    0.33
    POSITIVE LOGITS
    0.44
    7
    0.41
    1
    0.41
    2
    0.41
    4
    0.38
    3
    0.38
    0
    0.38
    9
    0.36
    6
    0.36
    5
    0.34
    Activations Density 0.003%

    No Known Activations