© 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. 93177
    Prev
    Next
    INDEX
    Explanations

    negative superlatives

    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
    CONCLUS
    -0.93
     prate
    -0.93
    可惜
    -0.90
    hhhh
    -0.88
     zalando
    -0.86
     ($('#
    -0.86
     hek
    -0.84
     矢量
    -0.84
    hhhhhhhh
    -0.84
     ROMA
    -0.83
    POSITIVE LOGITS
     worst
    6.56
     worse
    6.53
    worst
    5.28
     Worst
    5.00
     Worse
    4.94
    Worst
    4.94
    worse
    4.91
    Worse
    4.66
     peor
    3.91
     WOR
    3.70
    Activations Density 0.054%

    No Known Activations