© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7542
    Prev
    Next
    INDEX
    Explanations

    **Explaining Neuron Behavior.****1. MAXIMUM ACTIVATING TOKENS:**- `and`- `there`- `a`- `achieve`- `financing`- `Zy` (This looks like an unusual token, possibly noise or very specific. I will note it but focus on clearer patterns.)- `dialogue`- `System`- `your`- `

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    т
    1.03
    ات
    1.01
     Kochubei
    0.98
     CrL
    0.98
    証明
    0.94
     szolg
    0.90
     گاه
    0.88
    t
    0.84
    ية
    0.84
     Zeitpunkt
    0.84
    POSITIVE LOGITS
    ing
    0.72
    此处
    0.71
     in
    0.69
    erk
    0.69
    iann
    0.68
     aurez
    0.68
     nutr
    0.67
     accad
    0.66
    ann
    0.65
    োর
    0.64
    Activations Density 0.000%

    No Known Activations