© 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. 31966
    Prev
    Next
    INDEX
    Explanations

    see why

    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
    C
    0.93
     ન
    0.89
     Đ
    0.88
    dB
    0.86
    B
    0.86
    น
    0.83
    Ç
    0.83
    G
    0.81
    γκ
    0.80
    soever
    0.80
    POSITIVE LOGITS
    holds
    0.82
     există
    0.81
    плення
    0.80
     semplici
    0.79
    сной
    0.79
     собі
    0.79
     potrebné
    0.78
    bbero
    0.77
     mittels
    0.77
    šću
    0.77
    Activations Density 0.009%

    No Known Activations