© 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. 11182
    Prev
    Next
    INDEX
    Explanations

    Option following blank

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

    This neuron primarily activates on numeric tokens and alphanumeric identifiers (e.g. numbers, codes, version or section references).

    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
     decadent
    0.64
     encircled
    0.61
     rosemary
    0.58
     hausse
    0.57
     terroir
    0.57
     démarrage
    0.57
    <unused5>
    0.57
    <unused45>
    0.57
     apricot
    0.57
     matchs
    0.57
    POSITIVE LOGITS
    }
    0.64
     }
    0.62
    at
    0.61
    ase
    0.59
    W
    0.59
    At
    0.59
    Dup
    0.59
    Un
    0.58
    I
    0.58
    n
    0.57
    Activations Density 0.048%

    No Known Activations