© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 3037
    Prev
    Next
    INDEX
    Explanations

    flow and structure

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

    The neuron spotlights high‐impact buzzwords and positive/value-laden terms—e.g. words about negotiation, professionalism, improvement, transparency, harmony, etc.

    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
     (
    0.63
     
    0.63
     You
    0.62
     but
    0.60
     pero
    0.58
    -
    0.57
    ?
    0.56
     mà
    0.55
     này
    0.54
    1
    0.54
    POSITIVE LOGITS
    <unused301>
    0.75
    <unused332>
    0.75
    <unused292>
    0.70
    <unused334>
    0.68
    <unused331>
    0.68
    <unused1887>
    0.67
    <unused199>
    0.66
    <unused309>
    0.66
    <unused702>
    0.66
    <unused99>
    0.65
    Activations Density 0.253%

    No Known Activations