© 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. 1972
    Prev
    Next
    INDEX
    Explanations

    low risk, competition, acidity

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

    The neuron fires on adjectival modifiers that signal smallness or low intensity (e.g. “minimal,” “low,” “light,” “small,” “moderate”).

    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
    。
    0.66
    Hun
    0.58
     Nasıl
    0.53
    Ela
    0.52
    Để
    0.51
    Pentru
    0.50
     sogen
    0.50
     najważ
    0.49
    Jos
    0.49
     nejen
    0.49
    POSITIVE LOGITS
     $(<
    0.62
     conductivity
    0.60
     respiration
    0.60
    sided
    0.59
    mente
    0.59
    isable
    0.58
     reflectance
    0.57
    𝘆
    0.57
     hysteresis
    0.57
     birefringence
    0.57
    Activations Density 0.001%

    No Known Activations