© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113099
    Prev
    Next
    INDEX
    Explanations

    writing and assessing situations

    np_acts-logits-general · gemini-2.5-flash-lite

    specific symbols or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    امه
    0.52
    ي
    0.51
    ᱭ
    0.48
    娜
    0.47
    ర్
    0.46
    числения
    0.44
    jupyter
    0.43
    骄
    0.43
    Browse
    0.43
    井
    0.43
    POSITIVE LOGITS
     pédicule
    0.50
     souci
    0.50
     tapi
    0.49
     rilev
    0.48
     ancak
    0.48
     puis
    0.48
     namun
    0.45
     regol
    0.45
     MDLVertex
    0.45
     குறிப்பிட்ட
    0.45
    Activations Density 0.001%

    No Known Activations