© 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. 14720
    Prev
    Next
    INDEX
    Explanations

    introductions and meeting people

    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
    ル
    0.92
    ሎችን
    0.88
    تها
    0.88
    에서의
    0.88
     সমস্যাবলী
    0.88
    تو
    0.84
    äume
    0.83
    <unused69>
    0.79
    odnev
    0.79
    imantan
    0.79
    POSITIVE LOGITS
     who
    0.88
     really
    0.85
     terrestrial
    0.83
     LinkedIn
    0.83
     grandiose
    0.82
     société
    0.81
     চেন
    0.79
    五十
    0.79
    परि
    0.79
     monster
    0.78
    Activations Density 0.232%

    No Known Activations