© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7817
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    The neuron fires on conversational address tokens—especially second-person pronouns (“you,” “your”) and similar interactive/discourse markers like “thanks,” “sounds,” “awesome,” etc.

    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_31_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
     例文帳に追加
    0.64
    –
    0.64
    <unused11>
    0.63
    例文帳に追加
    0.63
     \"
    0.57
     "'
    0.57
    )'
    0.56
    ...'
    0.55
    ]'
    0.54
    โครง
    0.52
    POSITIVE LOGITS
    ’,
    0.89
     @
    0.85
    …’
    0.82
    “”
    0.80
    ,’
    0.80
     “,
    0.79
    ’’
    0.79
     ‘
    0.78
    <code>
    0.76
    ’?
    0.75
    Activations Density 0.161%

    No Known Activations