© 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. 38299
    Prev
    Next
    INDEX
    Explanations

    `+/-` and `+=` symbols; numbers; punctuation

    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
     nanos
    -0.80
    Race
    -0.79
    IC
    -0.78
    PageModule
    -0.77
     Race
    -0.77
    OS
    -0.77
     @"/
    -0.77
    Fort
    -0.77
    らせ
    -0.75
    Cross
    -0.75
    POSITIVE LOGITS
     Commemor
    0.87
     hama
    0.75
    rayage
    0.72
     impractica
    0.71
     cala
    0.71
     baku
    0.69
     dizem
    0.69
     KES
    0.68
     connecter
    0.67
     carab
    0.66
    Activations Density 0.022%

    No Known Activations