© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2899
    Prev
    Next
    INDEX
    Explanations

    military advisor

    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
     randomised
    -0.74
     tolerated
    -0.73
     randomized
    -0.73
    inquiry
    -0.69
     Investigator
    -0.68
    门外
    -0.67
    ลง
    -0.66
    Ankara
    -0.65
     Ше
    -0.63
     Investigators
    -0.63
    POSITIVE LOGITS
    itory
    0.83
    ليج
    0.77
    Posts
    0.76
    Support
    0.75
     Kuwait
    0.73
    lasty
    0.72
    بوك
    0.72
    clone
    0.72
    BIT
    0.71
    ünste
    0.71
    Activations Density 0.043%

    No Known Activations