© 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. 107671
    Prev
    Next
    INDEX
    Explanations

    HTML head tags

    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
     avoit
    -1.09
     embodied
    -0.92
    arikat
    -0.86
     dibutuhkan
    -0.85
     león
    -0.84
     adequate
    -0.84
     nocy
    -0.84
    uyla
    -0.84
     cubano
    -0.83
     mixing
    -0.82
    POSITIVE LOGITS
     můžete
    0.77
     sermon
    0.77
    ddots
    0.76
    UD
    0.75
    ('/');
    0.75
    END
    0.73
     Toul
    0.73
     Sustainability
    0.72
    ächlich
    0.72
    ActionEvent
    0.71
    Activations Density 0.002%

    No Known Activations