© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12413
    Prev
    Next
    INDEX
    Explanations

    connections between entities

    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
    ਲ
    0.53
    د
    0.52
     horrors
    0.48
    ق
    0.48
     maniac
    0.47
    inz
    0.47
    д
    0.47
    يل
    0.47
    geb
    0.46
    一個
    0.46
    POSITIVE LOGITS
     ойноо
    0.46
     cặp
    0.44
     giữa
    0.44
     Positioning
    0.43
     між
    0.43
    ওয়্যার
    0.42
     thiện
    0.42
    数为
    0.42
    ５
    0.42
     уйнау
    0.41
    Activations Density 0.019%

    No Known Activations