© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11134
    Prev
    Next
    INDEX
    Explanations

    if you

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

    This neuron fires on “if you” conditional constructions (i.e. second‐person conditional phrases).

    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_31_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
     EVERYTHING
    0.75
     someone
    0.72
     Someone
    0.71
     €,
    0.67
     NO
    0.66
     prostu
    0.65
     +,
    0.63
     충분
    0.63
     somebody
    0.63
     tanque
    0.62
    POSITIVE LOGITS
    soci
    0.68
    being
    0.68
    哲学
    0.62
     olmak
    0.60
    心の
    0.60
    均为
    0.59
    人文
    0.58
     being
    0.57
     albeit
    0.57
    albeit
    0.57
    Activations Density 0.120%

    No Known Activations