© 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. 7248
    Prev
    Next
    INDEX
    Explanations

    ste start

    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
    <0x80>
    2.08
     NUE
    1.88
    يير
    1.84
     produt
    1.83
     sustain
    1.82
     тех
    1.77
     стоимо
    1.73
     tras
    1.73
     insc
    1.73
     Amendments
    1.72
    POSITIVE LOGITS
    ج
    2.05
    tır
    2.03
    ות
    1.95
    א
    1.93
    猬
    1.90
    قوم
    1.89
    pä
    1.88
    锑
    1.87
    }$
    1.85
    นี่
    1.80
    Activations Density 0.514%

    No Known Activations