© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138506
    Prev
    Next
    INDEX
    Explanations

    phosphorylation, training, Gauck, languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    我
    0.67
    有
    0.50
    是
    0.46
    章
    0.45
     יה
    0.44
    CCION
    0.44
    振
    0.44
    मैंने
    0.42
    ג
    0.42
    具
    0.42
    POSITIVE LOGITS
    Населення
    0.50
     thirds
    0.50
     autocl
    0.48
     arrivée
    0.47
    orifice
    0.47
    -$\
    0.47
    fcast
    0.46
    تال
    0.46
     shampoos
    0.46
    க்கால்
    0.46
    Activations Density 0.002%

    No Known Activations