© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15565
    Prev
    Next
    INDEX
    Explanations

    impact of

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

    This neuron detects nouns (and their following “of”) that signal discussion of outcomes or impacts—e.g. “consequences of,” “impact of,” or “effect of.”

    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
     только
    0.80
     functionalities
    0.78
    乐趣
    0.76
     tylko
    0.75
     সাহায
    0.75
    '!
    0.74
    з
    0.73
    է
    0.73
     only
    0.71
     helps
    0.70
    POSITIVE LOGITS
     abortion
    0.90
     Brexit
    0.87
     Watergate
    0.86
    Brexit
    0.84
    abortion
    0.84
     polarisation
    0.83
     Putin
    0.82
     polarization
    0.81
     glyphosate
    0.80
     Hezbollah
    0.78
    Activations Density 0.051%

    No Known Activations