© 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. 8296
    Prev
    Next
    INDEX
    Explanations

    is a or are

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

    This neuron picks out procedural or instructional text—especially segments phrased as questions or imperatives (e.g. “Where can I…?” or “To do this, enter…”).

    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
    ;
    0.73
     —
    0.68
    —
    0.64
    t
    0.64
    ’
    0.63
     -
    0.61
     stunning
    0.61
     :
    0.61
     dramatically
    0.61
     --
    0.60
    POSITIVE LOGITS
     możliwe
    0.87
     jakości
    0.86
     potrz
    0.81
     attrezz
    0.81
    ですか
    0.80
     acudir
    0.80
    indak
    0.79
     sprzę
    0.79
     hermoso
    0.78
     enak
    0.78
    Activations Density 0.086%

    No Known Activations