© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7273
    Prev
    Next
    INDEX
    Explanations

    Urgent/

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

    The neuron fires strongly on words carrying an evaluative or promotional tone (comparisons, positives, appeals), e.g. “as,” “compared,” “reliability,” “attractions,” “importance,” “favour.”

    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
    ם
    0.95
    ر
    0.84
    ادية
    0.78
     immers
    0.76
    sächlich
    0.74
     আবেদ
    0.74
    יו
    0.73
    settes
    0.72
     abb
    0.71
    جل
    0.71
    POSITIVE LOGITS
     Dirección
    0.83
    AHN
    0.83
    ASS
    0.82
     synapse
    0.75
     windmill
    0.74
    ം
    0.74
    ്രി
    0.73
     Kernel
    0.73
     abrang
    0.71
     Speed
    0.70
    Activations Density 0.000%

    No Known Activations