© 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. 69833
    Prev
    Next
    INDEX
    Explanations

    citations like [*x*]

    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
     now
    -0.96
    Nic
    -0.83
     fact
    -0.81
     questi
    -0.79
    Ver
    -0.79
    Una
    -0.77
    vocations
    -0.76
     „
    -0.76
    Uri
    -0.76
    Link
    -0.75
    POSITIVE LOGITS
     bénéficiaire
    0.97
    Andres
    0.94
     besoins
    0.92
    Fungsi
    0.89
    moins
    0.88
     ビキニ
    0.88
    anians
    0.87
    Avis
    0.87
     moi
    0.86
     ウィメンズ
    0.85
    Activations Density 0.099%

    No Known Activations