© 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. 4492
    Prev
    Next
    INDEX
    Explanations

    pleasure

    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
    smanship
    2.27
    e
    2.19
    ीय
    2.05
    ی
    1.94
     coalgebras
    1.91
    ির
    1.91
    y
    1.90
    taus
    1.88
    songs
    1.83
    s
    1.82
    POSITIVE LOGITS
    दायक
    2.31
     urination
    2.16
    IK
    2.09
    ൃത്ത
    2.08
     daqui
    2.06
    わたし
    2.00
    Ṕ
    2.00
    رة
    1.99
     mümkün
    1.99
    ہنی
    1.97
    Activations Density 0.014%

    No Known Activations