© 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. 5105
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to marketing‐style reassurance phrases that promise to guide the customer (e.g. “we take things a step further by ensuring that you know which … is best for your needs”).

    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
     
    1.43
     a
    0.92
     (
    0.86
     m
    0.85
     \
    0.85
    ’
    0.84
     `
    0.83
     was
    0.83
    '
    0.83
     $\
    0.82
    POSITIVE LOGITS
    <unused462>
    1.20
    <unused458>
    1.16
    <unused467>
    1.15
    <unused402>
    1.14
    <unused654>
    1.13
    <unused481>
    1.11
    <unused490>
    1.11
    <unused480>
    1.10
    <unused465>
    1.09
    <unused99>
    1.06
    Activations Density 0.018%

    No Known Activations