© 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. 115543
    Prev
    Next
    INDEX
    Explanations

    on followed by callback methods

    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
     illimit
    -0.98
     massiv
    -0.94
     intensif
    -0.92
     linge
    -0.90
     prati
    -0.89
     forment
    -0.89
     sirop
    -0.88
     brillant
    -0.88
     valide
    -0.85
     infin
    -0.84
    POSITIVE LOGITS
    Other
    0.93
     weshalb
    0.90
     Other
    0.90
     before
    0.89
     dibawah
    0.86
     urgencia
    0.85
    Configuration
    0.83
     Some
    0.83
    Still
    0.83
     creating
    0.82
    Activations Density 0.003%

    No Known Activations