© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115286
    Prev
    Next
    INDEX
    Explanations

    improves gallbladder

    np_acts-logits-general · gemini-2.5-flash-lite

    Chapel style and teachings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chend
    0.48
     SLR
    0.46
     Xperia
    0.41
    尾
    0.41
    hing
    0.40
     ஒப்ப
    0.39
     хоккей
    0.39
    旋
    0.39
    love
    0.38
     Koval
    0.38
    POSITIVE LOGITS
    йд
    0.50
    राजस्थान
    0.50
     जरुरत
    0.49
    ्लाई
    0.47
    Referencias
    0.45
    אם
    0.44
     Processing
    0.43
     Delayed
    0.43
    Nec
    0.43
     adverts
    0.43
    Activations Density 0.000%

    No Known Activations