© 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. 209694
    Prev
    Next
    INDEX
    Explanations

    alternating colors or concepts

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

    contrasting phrases

    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
    Ils
    0.48
     বৃদ্ধ
    0.46
    Wedding
    0.46
    !='
    0.46
     Wedding
    0.44
    ಡುವುದ
    0.43
    Mutation
    0.43
    Replace
    0.43
     Cigar
    0.43
    Secret
    0.42
    POSITIVE LOGITS
     istek
    0.54
     полномо
    0.53
     rekan
    0.50
     szí
    0.49
     millennial
    0.49
    ګ
    0.49
     таки
    0.48
     применя
    0.48
     necesit
    0.48
     IQR
    0.47
    Activations Density 0.001%

    No Known Activations