© 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. 79520
    Prev
    Next
    INDEX
    Explanations

    skills and confidence

    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
    она
    0.52
    𝗵
    0.48
    ке
    0.47
    щення
    0.47
    િતા
    0.47
    制限
    0.47
     reklam
    0.46
     Temperaturen
    0.46
    üks
    0.46
    ол
    0.45
    POSITIVE LOGITS
    :
    0.57
     harbor
    0.54
    っており
    0.49
     पाने
    0.46
    Malay
    0.46
    ].
    0.46
     Maryland
    0.44
     scientist
    0.44
     signup
    0.44
     pair
    0.43
    Activations Density 0.001%

    No Known Activations