© 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. 33449
    Prev
    Next
    INDEX
    Explanations

    Apache license or Apache web server

    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
    onghi
    -0.86
     militer
    -0.79
    posta
    -0.78
    juni
    -0.78
     pasien
    -0.77
    $",
    -0.76
    тату
    -0.76
    スプレ
    -0.75
    עו
    -0.75
    viem
    -0.75
    POSITIVE LOGITS
    WSGI
    0.89
    .+
    0.88
    inary
    0.85
     vermic
    0.84
     arşivlendi
    0.81
    ont
    0.79
    Wiring
    0.78
     paysage
    0.77
    ické
    0.77
    佟
    0.77
    Activations Density 0.001%

    No Known Activations