© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5040
    Prev
    Next
    INDEX
    Explanations

    model for sentiment analysis

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

    This neuron detects list-style or enumerative sequences—particularly numeric tokens (like years, counts, or digits) and their surrounding punctuation—used to present facts or qualifications in a document.

    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
     éste
    0.77
     efectuar
    0.76
     prepd
    0.75
     initialise
    0.69
     éstos
    0.68
     solns
    0.67
     dgn
    0.67
     ésta
    0.66
     plantel
    0.66
     costituito
    0.66
    POSITIVE LOGITS
     Ubuy
    0.82
     spokesperson
    0.65
     YouTuber
    0.62
    ²,
    0.57
    <unused2126>
    0.56
    !),
    0.56
     foodie
    0.54
    <unused2107>
    0.54
    <unused2129>
    0.54
     чолові
    0.54
    Activations Density 0.007%

    No Known Activations