© 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. 54257
    Prev
    Next
    INDEX
    Explanations

    finally, Min, vital

    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
     Washington
    0.42
    личи
    0.42
     Homo
    0.41
    Á
    0.41
     Seoul
    0.40
    statusBar
    0.40
     Columbia
    0.39
     Wat
    0.38
    ice
    0.38
    ave
    0.38
    POSITIVE LOGITS
     非常
    0.57
    𝘨
    0.54
    મિ
    0.53
     перевоз
    0.52
     ବି
    0.52
     सुद्धा
    0.52
     प्रतिनि
    0.50
    𒈨
    0.50
     ν
    0.50
     consolid
    0.50
    Activations Density 0.000%

    No Known Activations