© 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. 9116
    Prev
    Next
    INDEX
    Explanations

    python `F` and `nn` imports

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

    This neuron detects the start of a new numbered or bulleted list item or section—that is, the very first content word in each list entry.

    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
    ッキ
    0.92
    αν
    0.87
    меется
    0.86
    ാ
    0.86
    ﻨ
    0.85
    ம்
    0.81
    ながら
    0.80
    cidas
    0.79
    ിൽ
    0.79
    حب
    0.79
    POSITIVE LOGITS
    }])
    0.83
     mức
    0.82
    {{
    0.82
    }
    0.80
    }"]
    0.77
     os
    0.76
    };//
    0.75
     Fifteen
    0.74
    amount
    0.74
    =
    0.74
    Activations Density 0.000%

    No Known Activations