© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7276
    Prev
    Next
    INDEX
    Explanations

    blog post URLs

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

    This neuron flags tokens that include apostrophes (i.e. contractions or similar ’-containing forms).

    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
    .''
    0.77
    '."
    0.75
     -
    0.74
     ''
    0.73
    ,''
    0.66
    ''
    0.65
    ...'
    0.64
    '
    0.63
    -'
    0.63
     групи
    0.62
    POSITIVE LOGITS
     하지만
    0.90
     ‘
    0.82
     blog
    0.82
    blog
    0.82
     Blog
    0.81
    =’
    0.76
    Blog
    0.75
    ه‌ی
    0.72
     blogs
    0.70
     blogger
    0.70
    Activations Density 1.836%

    No Known Activations