© 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. 4599
    Prev
    Next
    INDEX
    Explanations

    sequences after English words

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

    The neuron responds strongly to uncommon, content‐bearing words (e.g. “going,” “large,” “off topic,” “found,” “obtained”), i.e. it flags rare or infrequently used tokens.

    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
     UNIV
    0.95
    ன்மையான
    0.84
     bbq
    0.84
     PROCED
    0.83
     نیست
    0.82
     influência
    0.80
    ════
    0.79
     安心
    0.78
     completos
    0.77
     TERMIN
    0.76
    POSITIVE LOGITS
    Aby
    0.73
    За
    0.72
    he
    0.71
    ма
    0.71
    Mi
    0.71
    Pada
    0.71
    Prz
    0.70
    Он
    0.69
    ্যোগ
    0.69
    Aw
    0.68
    Activations Density 0.000%

    No Known Activations