© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82244
    Prev
    Next
    INDEX
    Explanations

    template code and assignments

    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
     всеки
    -0.84
     Verkauf
    -0.83
    monies
    -0.83
     Gummies
    -0.83
    čeno
    -0.82
     Raising
    -0.79
     peças
    -0.79
    ølge
    -0.77
     calculate
    -0.77
    徬
    -0.77
    POSITIVE LOGITS
    回事
    0.83
    regu
    0.81
     settimane
    0.79
     shuffling
    0.76
    kebox
    0.75
     LQ
    0.75
     domic
    0.75
     เบ
    0.75
     clique
    0.74
     Bete
    0.73
    Activations Density 0.000%

    No Known Activations