© 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. 6399
    Prev
    Next
    INDEX
    Explanations

    overestimate, determine, Google, liberals, teenagers

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

    The neuron strongly activates on contentful action words (i.e. verbs denoting key actions, in various tenses and forms).

    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
    ста
    0.84
     простой
    0.81
     coisa
    0.79
    лю
    0.78
     ткань
    0.77
    ته
    0.77
    коло
    0.73
    춧
    0.73
    κε
    0.71
     сро
    0.68
    POSITIVE LOGITS
     և
    0.84
     Didn
    0.80
     ለ
    0.78
    anatom
    0.78
     Wit
    0.78
     말했다
    0.77
     живело
    0.77
    Didn
    0.76
     inhum
    0.76
     Kishore
    0.72
    Activations Density 0.000%

    No Known Activations