© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50438
    Prev
    Next
    INDEX
    Explanations

    negative evaluations

    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
     awesome
    -1.14
     cool
    -1.10
    zel
    -1.06
     crazy
    -1.05
     nice
    -1.05
     fancy
    -1.04
     sexy
    -1.02
    ish
    -1.01
     silly
    -0.98
     kinda
    -0.96
    POSITIVE LOGITS
     worse
    1.49
     cringe
    1.49
     Worse
    1.38
    Worse
    1.36
     worst
    1.34
     Worst
    1.23
    Worst
    1.19
    worse
    1.10
     настолько
    1.10
     peggio
    1.08
    Activations Density 0.086%

    No Known Activations