© 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. 8098
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    sai
    0.56
    sse
    0.54
    toggle
    0.54
     aperture
    0.53
    kta
    0.53
    adav
    0.52
    s
    0.50
    slack
    0.50
    quant
    0.50
    cav
    0.49
    POSITIVE LOGITS
    ने
    0.46
    的事情
    0.43
     perfectamente
    0.42
    라고
    0.42
     últimas
    0.42
    墓志
    0.42
     पिछले
    0.42
    지고
    0.42
    란
    0.42
    㝡
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.