© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 37918
    Prev
    Next
    INDEX
    Explanations

    and/but/albeit followed by qualifier

    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_262k_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
    ం
    0.91
    มีความ
    0.89
     ofthe
    0.89
     spindles
    0.87
     fiasco
    0.86
    ของ
    0.85
    ofthe
    0.84
    o
    0.84
     fillets
    0.83
     ملی
    0.82
    POSITIVE LOGITS
    Defined
    0.88
    defined
    0.84
    ‌ترین
    0.82
    cov
    0.82
    కి
    0.81
     Reputation
    0.80
    اپنی
    0.79
    delen
    0.77
     Delegation
    0.77
    cale
    0.76
    Activations Density 0.084%

    No Known Activations