© 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. 47723
    Prev
    Next
    INDEX
    Explanations

    Competitors, structures, Keras

    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
     LOTRAchievement
    0.48
    泼
    0.48
    敀
    0.48
     στά
    0.48
     розы
    0.48
    nofollow
    0.47
     বিএনপির
    0.47
     ስ
    0.45
     Zeits
    0.45
    ياب
    0.45
    POSITIVE LOGITS
     building
    0.49
     fjord
    0.46
     glass
    0.46
     information
    0.45
    fd
    0.45
    これ
    0.45
     epidemic
    0.43
     summer
    0.43
     campus
    0.42
     Plus
    0.42
    Activations Density 0.002%

    No Known Activations