© 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. 116100
    Prev
    Next
    INDEX
    Explanations

    date and state names

    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
    ϑ
    -0.86
    gradable
    -0.83
     bądź
    -0.81
    allas
    -0.78
    web
    -0.77
    にく
    -0.77
     البد
    -0.76
    Web
    -0.75
     straightforward
    -0.72
    *}$
    -0.72
    POSITIVE LOGITS
    institu
    0.97
    pellier
    0.89
    kezi
    0.82
    Luxem
    0.80
    ketten
    0.80
     Eigentü
    0.79
    {};
    0.78
    wiście
    0.77
    ImageIO
    0.77
    Dise
    0.77
    Activations Density 0.008%

    No Known Activations