© 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. 15570
    Prev
    Next
    INDEX
    Explanations

    program execution state

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

    The neuron fires strongly at words marking the starts of new topical sections or paragraph breaks (i.e. topic‐shift boundary 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
    蹿
    0.87
    Feeding
    0.82
    Sun
    0.78
    یہ
    0.76
    سے
    0.76
    u
    0.76
    ق
    0.75
    How
    0.75
    SUN
    0.75
    atten
    0.74
    POSITIVE LOGITS
    лық
    0.95
     professora
    0.88
    тные
    0.88
     ďal
    0.87
     erros
    0.86
     общения
    0.86
    ﺖ
    0.85
    ны
    0.84
     Kisan
    0.84
     예를
    0.84
    Activations Density 0.000%

    No Known Activations