© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10968
    Prev
    Next
    INDEX
    Explanations

    lists of examples or details

    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_40_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
    :
    0.69
     "
    0.54
    ’
    0.48
    0.45
     very
    0.44
     “
    0.43
     '
    0.42
     cosidd
    0.42
     *
    0.41
      
    0.40
    POSITIVE LOGITS
    睗
    0.50
    その他
    0.48
    等等
    0.48
     など
    0.46
    等多
    0.45
     различными
    0.44
     통한
    0.44
    灲
    0.44
     которыми
    0.44
     సంబంధించిన
    0.44
    Activations Density 2.433%

    No Known Activations