© 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. 136965
    Prev
    Next
    INDEX
    Explanations

    physical locations and states

    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
     jawaban
    0.47
    клада
    0.46
     sumptuous
    0.46
    ट
    0.45
    人
    0.42
     university
    0.42
     northern
    0.41
     thanh
    0.41
    도
    0.41
    ן
    0.40
    POSITIVE LOGITS
     Kroger
    0.50
     τέ
    0.48
     Κ
    0.47
     لكل
    0.47
     Derrick
    0.46
     Qt
    0.46
     କ
    0.46
     χρησιμοποι
    0.46
     będą
    0.45
    implemented
    0.45
    Activations Density 0.010%

    No Known Activations