© 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. 7078
    Prev
    Next
    INDEX
    Explanations

    digital currency

    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
    itica
    -0.80
     inau
    -0.80
     sib
    -0.79
     Cicero
    -0.76
    scn
    -0.76
     elixir
    -0.75
     manly
    -0.75
     スケ
    -0.74
    ]='\
    -0.73
    Chain
    -0.72
    POSITIVE LOGITS
     kemampuan
    0.78
     бухгал
    0.77
    𝒓
    0.76
    -->
    
    0.74
     delantera
    0.73
     христи
    0.71
    VOID
    0.71
    ష
    0.69
    </s>
    0.69
     resep
    0.68
    Activations Density 0.000%

    No Known Activations