© 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-262K
    7. 8998
    Prev
    Next
    INDEX
    Explanations

    Mental Health America

    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
     古
    0.75
     Arist
    0.73
    лькі
    0.72
    ক
    0.72
     Си
    0.71
     প্রাণ
    0.70
     Socrates
    0.70
    ктора
    0.69
     மதி
    0.68
    اعر
    0.68
    POSITIVE LOGITS
    s
    1.13
    om
    1.01
    ab
    0.89
    ের
    0.82
     тобто
    0.77
    sign
    0.76
    ly
    0.76
     IMO
    0.75
    ਾ
    0.75
    IMO
    0.74
    Activations Density 0.000%

    No Known Activations