© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63470
    Prev
    Next
    INDEX
    Explanations

    code delimiters or variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ֢
    -0.89
    꾼
    -0.85
    マイズ
    -0.83
    Воспита
    -0.81
    Веду
    -0.81
    彣
    -0.81
    رفة
    -0.80
    něte
    -0.79
    junto
    -0.78
    Sito
    -0.78
    POSITIVE LOGITS
    ={()
    0.86
    cepatan
    0.84
     espagne
    0.81
    Drum
    0.79
    aujourd
    0.79
    ?''
    0.78
    OR
    0.77
     pami
    0.77
     masak
    0.77
    Wind
    0.77
    Activations Density 0.000%

    No Known Activations