© 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. 7695
    Prev
    Next
    INDEX
    Explanations

    text formatting separators

    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
    ו
    1.89
    ます
    1.69
    언
    1.63
    ن
    1.59
    الإ
    1.55
    המ
    1.54
    الم
    1.53
    起
    1.53
    其他
    1.52
    يج
    1.51
    POSITIVE LOGITS
     fontstyle
    1.63
    casualties
    1.60
     ventas
    1.52
    ൃത്ത
    1.50
     Acá
    1.50
    bibliography
    1.46
    рино
    1.44
    क्टूबर
    1.42
    Qaeda
    1.41
     Öffentlichkeit
    1.41
    Activations Density 0.074%

    No Known Activations