© 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. 5372
    Prev
    Next
    INDEX
    Explanations

    equation links

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

    This neuron activates on tokens that begin with a capital letter (e.g., proper nouns or sentence-initial words).

    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
     များ
    0.77
     tweaks
    0.73
     Polity
    0.71
    细
    0.70
     টান
    0.68
     jigs
    0.67
     indem
    0.66
    '
    0.64
     associations
    0.64
     BELOW
    0.63
    POSITIVE LOGITS
    rd
    0.95
    rp
    0.84
    nn
    0.80
     avanzar
    0.80
    dengan
    0.78
    counting
    0.78
    sk
    0.77
    stanbul
    0.77
     öğret
    0.77
    rH
    0.77
    Activations Density 0.000%

    No Known Activations