© 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. 7099
    Prev
    Next
    INDEX
    Explanations

    of every

    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
    '
    1.23
    ।
    0.97
    berg
    0.96
    नामा
    0.95
    ()'
    0.94
    ic
    0.93
    .
    0.92
    ,
    0.92
    ವಾದ
    0.90
    iz
    0.89
    POSITIVE LOGITS
    were
    1.06
     are
    1.05
    you
    1.02
     amelyek
    1.02
     WERE
    1.01
     )
    1.00
    ிருக்கின்றன
    0.97
    理
    0.96
    these
    0.95
     imbalances
    0.95
    Activations Density 0.298%

    No Known Activations