© 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. 1015
    Prev
    Next
    INDEX
    Explanations

    anybody somebody everybody

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

    The neuron is strongly activated by basic high-frequency action verbs (e.g. common “do,” “go,” “get,” “back,” “talk,” etc.).

    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
     également
    0.84
     ancak
    0.82
     tuttavia
    0.76
     cuya
    0.74
     אך
    0.71
     számos
    0.71
     aka
    0.70
     &/
    0.69
     نیز
    0.68
     cuyo
    0.68
    POSITIVE LOGITS
    Anybody
    0.92
    Everybody
    0.90
    Somebody
    0.89
    這樣子
    0.88
    そういう
    0.87
     Anybody
    0.84
     Somebody
    0.84
    こういう
    0.82
     everybody
    0.82
    すごく
    0.81
    Activations Density 0.000%

    No Known Activations