© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15179
    Prev
    Next
    INDEX
    Explanations

    alternative to like sugar

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

    The neuron fires on the main “definitional” verbs in encyclopedic‐style intro lines—i.e. verbs that say what a person or thing is known for or does (appearing, supporting, published, contributed, 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
     Tabelle
    0.93
     kleur
    0.85
     grosseur
    0.84
     celebración
    0.80
    дни
    0.80
     ongeveer
    0.80
    오는
    0.79
    ا
    0.79
     acteurs
    0.79
     colori
    0.78
    POSITIVE LOGITS
    ness
    0.93
    padding
    0.82
    _
    0.82
    \;
    0.77
    .
    0.77
     (\"
    0.76
    .\
    0.75
     incurs
    0.73
    rist
    0.73
    ned
    0.73
    Activations Density 0.000%

    No Known Activations