© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32759
    Prev
    Next
    INDEX
    Explanations

    tid followed by wave or disruption

    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
     direito
    -0.79
    denial
    -0.76
    逃避
    -0.71
     مدينة
    -0.70
     ceiling
    -0.70
    避け
    -0.69
    瞞
    -0.69
    mushroom
    -0.69
     otomatis
    -0.68
    Kush
    -0.67
    POSITIVE LOGITS
     tid
    1.16
    Wave
    1.08
     Wave
    0.96
    bits
    0.90
    wave
    0.89
    Bits
    0.87
    optim
    0.85
     wave
    0.85
    Optim
    0.84
     Tid
    0.84
    Activations Density 0.013%

    No Known Activations