© 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-16K
    7. 6803
    Prev
    Next
    INDEX
    Explanations

    technical commands or identifiers

    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_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
    -
    1.05
    ’
    0.86
    ري
    0.76
    ه
    0.75
    ли
    0.74
    ON
    0.73
    \
    0.68
    را
    0.68
    EN
    0.67
    –
    0.66
    POSITIVE LOGITS
     ibang
    0.54
     bruke
    0.52
    ı
    0.52
     kirjo
    0.50
    ান্তরিত
    0.50
     Publ
    0.49
     Horticultural
    0.49
     হইয়
    0.48
     iub
    0.48
     sepatu
    0.48
    Activations Density 0.064%

    No Known Activations