© 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. 15165
    Prev
    Next
    INDEX
    Explanations

    **The prompt appears to have been truncated.**Please provide the complete prompt. I need all four lists (TOP_POSITIVE_LOGITS, TOP_ACTIVATING_TEXTS, MAX_ACTIVATING_TOKENS, TOKENS_AFTER_MAX_ACTIVATING_TOKEN) to explain the neuron's behavior

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

    The neuron consistently spikes on the very first content word (token) at the start of a new sentence or paragraph.

    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
    רי
    0.81
    ри
    0.77
    사실
    0.75
    Всім
    0.75
     kwenye
    0.72
    рып
    0.72
    ס
    0.72
    চন্দ্র
    0.71
    ૩
    0.71
    metadata
    0.70
    POSITIVE LOGITS
     Ate
    0.94
    ное
    0.84
     것을
    0.83
     Søren
    0.77
     microw
    0.76
     autod
    0.76
     букмекер
    0.75
     overt
    0.74
     houden
    0.74
    '
    0.74
    Activations Density 0.000%

    No Known Activations