© 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. 109145
    Prev
    Next
    INDEX
    Explanations

    deals, discounts, and prices

    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
     their
    -0.85
     menjual
    -0.84
     analisis
    -0.79
     Selling
    -0.79
     功效
    -0.77
     vital
    -0.77
     arquite
    -0.75
    Exo
    -0.74
     duide
    -0.74
     it
    -0.74
    POSITIVE LOGITS
    шого
    0.77
    ご利用
    0.75
    ggar
    0.75
     Rem
    0.75
     Sünde
    0.74
    oubliez
    0.74
     Monaten
    0.73
    çam
    0.72
    事实上
    0.72
     EAR
    0.72
    Activations Density 0.008%

    No Known Activations