© 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. 346
    Prev
    Next
    INDEX
    Explanations

    python code imports

    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
     Malin
    -0.85
     Disponible
    -0.82
    ┋
    -0.78
    SBATCH
    -0.77
     Hubbard
    -0.76
     tula
    -0.75
    stro
    -0.75
     otim
    -0.74
     tirada
    -0.73
     nori
    -0.72
    POSITIVE LOGITS
     вещества
    0.97
     inicialmente
    0.87
    messages
    0.82
    곱
    0.81
    Stk
    0.80
     DMs
    0.78
     Hãy
    0.77
    Stolen
    0.77
    Ӣ
    0.76
    没有任何
    0.75
    Activations Density 0.010%

    No Known Activations