© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6325
    Prev
    Next
    INDEX
    Explanations

    std followed by semicolon

    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_31_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
    Think
    0.53
    呢
    0.53
     скажу
    0.51
    んですよ
    0.50
    ળી
    0.49
    legi
    0.49
     [*
    0.48
     думать
    0.48
     ciekaw
    0.48
    ()}
    0.47
    POSITIVE LOGITS
     Thai
    0.60
     knowledge
    0.58
    cerr
    0.57
    Thai
    0.57
     shutout
    0.57
     berarti
    0.55
    thai
    0.54
     ergonomic
    0.54
    仟
    0.54
     Caribbean
    0.53
    Activations Density 0.026%

    No Known Activations