© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127882
    Prev
    Next
    INDEX
    Explanations

    multilingual nature and specific phrases

    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
     saldo
    0.52
     usia
    0.47
    spersed
    0.46
    UCLEAR
    0.45
    ग
    0.44
     economy
    0.44
    cona
    0.43
    ēs
    0.43
    मिट
    0.43
    вар
    0.42
    POSITIVE LOGITS
     L
    0.54
     ي
    0.52
     ك
    0.49
     كتب
    0.47
     D
    0.47
     ($\
    0.46
     Z
    0.45
     සහ
    0.45
     Dr
    0.45
     excellent
    0.45
    Activations Density 0.003%

    No Known Activations