© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2670
    Prev
    Next
    INDEX
    Explanations

    else: structure

    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_40_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
    another
    0.45
     другому
    0.40
     altro
    0.38
     another
    0.38
    ዲ
    0.38
     ANOTHER
    0.38
    另一个
    0.37
     ಮತ್ತ
    0.37
     altra
    0.36
     matière
    0.36
    POSITIVE LOGITS
     InputDecoration
    0.34
    ftan
    0.34
    чал
    0.34
     ->
    0.33
    нин
    0.32
    ,}$
    0.32
     justiciable
    0.32
     सुप
    0.31
    нт
    0.31
     zaś
    0.31
    Activations Density 0.010%

    No Known Activations