© 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. 78119
    Prev
    Next
    INDEX
    Explanations

    Spring annotations and pytest

    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
     presentations
    -0.76
     pergunta
    -0.71
     dispositions
    -0.70
    
    -0.68
    ッピング
    -0.68
     tây
    -0.68
    醣
    -0.66
     therapies
    -0.66
     hoàn
    -0.65
    の人は
    -0.65
    POSITIVE LOGITS
    ＠
    1.17
    @
    1.03
     @
    1.00
    advice
    0.92
    -@
    0.92
    Advice
    0.88
    жих
    0.86
    (@
    0.83
    নে
    0.83
    .@
    0.82
    Activations Density 0.003%

    No Known Activations