© 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. 12234
    Prev
    Next
    INDEX
    Explanations

    public key, attribute successes, hand on, sun warms

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

    The neuron strongly activates on the very first token of a new sentence or clause.

    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
     V
    0.88
    k
    0.87
    O
    0.86
    u
    0.83
     Let
    0.81
     G
    0.80
     Biz
    0.79
     Party
    0.79
     Net
    0.77
     Ø
    0.77
    POSITIVE LOGITS
     comandante
    0.93
     acclaim
    0.90
    getBlueTeam
    0.89
     volcanoes
    0.89
    classifiers
    0.88
     waveguides
    0.88
    oblins
    0.88
     recruits
    0.86
    ]'
    0.86
    lineWidth
    0.85
    Activations Density 0.000%

    No Known Activations