© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66397
    Prev
    Next
    INDEX
    Explanations

    single market

    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
    âte
    -0.79
     tylko
    -0.69
    了出去
    -0.68
     convenio
    -0.68
     nadzie
    -0.68
     باشیم
    -0.68
    ؓ
    -0.68
     diplomacy
    -0.68
    conv
    -0.68
     спа
    -0.68
    POSITIVE LOGITS
     market
    1.73
     Single
    1.56
     Market
    1.56
    Market
    1.48
    market
    1.48
     Internal
    1.41
     MARKET
    1.35
    Single
    1.34
     single
    1.34
     internal
    1.32
    Activations Density 0.026%

    No Known Activations