© 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. 63834
    Prev
    Next
    INDEX
    Explanations

    Monthly archive listings

    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
     acrylique
    -0.81
     referrerpolicy
    -0.78
    värr
    -0.77
     inspiri
    -0.76
     embuti
    -0.74
     stellen
    -0.73
     sinar
    -0.73
    ʎ
    -0.73
    ebe
    -0.72
    }$}
    -0.71
    POSITIVE LOGITS
    Nb
    0.70
     overal
    0.69
     موج
    0.69
     mecha
    0.68
     Cavaliers
    0.68
    編
    0.67
     رسیده
    0.67
     proce
    0.66
     folgen
    0.66
    Dau
    0.66
    Activations Density 0.039%

    No Known Activations