© 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. 54196
    Prev
    Next
    INDEX
    Explanations

    Community Catal, numbers

    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
     especí
    -1.02
     pade
    -0.85
     endast
    -0.79
    utel
    -0.78
     atle
    -0.77
    Lithuan
    -0.76
     recic
    -0.75
    驤
    -0.75
     reisen
    -0.75
     کدام
    -0.75
    POSITIVE LOGITS
    ידות
    0.94
    stuff
    0.89
    udit
    0.83
     nível
    0.80
    haca
    0.79
     lineal
    0.79
    ongyang
    0.78
    olites
    0.76
    beast
    0.76
    ού
    0.76
    Activations Density 0.001%

    No Known Activations