© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106695
    Prev
    Next
    INDEX
    Explanations

    Dense layer definitions

    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_16_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
     Об
    0.55
    Об
    0.55
    डील
    0.53
    ຫມ
    0.52
     Để
    0.52
    も
    0.52
    ेलकम
    0.52
     lessen
    0.51
    ほとんど
    0.51
     ഇപ്പോൾ
    0.51
    POSITIVE LOGITS
     dije
    0.55
    ähne
    0.53
     dialects
    0.50
    AndroidResource
    0.48
     dah
    0.48
    forderungen
    0.48
     politische
    0.48
     monaster
    0.47
    ina
    0.46
    ك
    0.46
    Activations Density 0.001%

    No Known Activations