© 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. 41-GEMMASCOPE-2-RES-16K
    7. 7700
    Prev
    Next
    INDEX
    Explanations

    T phrases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
    戤
    0.64
    雒
    0.50
    妏
    0.49
    atha
    0.49
    昉
    0.49
    ंकज
    0.48
    喿
    0.48
     রেডিও
    0.47
     Atha
    0.46
    氿
    0.46
    POSITIVE LOGITS
     TP
    2.56
     TC
    2.47
     tf
    2.44
     Tucker
    2.44
     TF
    2.39
    Tucker
    2.36
    TP
    2.34
     tuberculosis
    2.31
     TB
    2.28
     Tü
    2.28
    Activations Density 1.065%

    No Known Activations