© 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. 980
    Prev
    Next
    INDEX
    Explanations

    chokes and locks

    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
     argparse
    -0.73
     Missoula
    -0.68
     liitty
    -0.68
    統領
    -0.68
     санк
    -0.66
    beros
    -0.66
     Sitemap
    -0.65
     EEU
    -0.65
    лось
    -0.63
    不等
    -0.63
    POSITIVE LOGITS
     counter
    1.01
     reversal
    0.94
    counter
    0.90
     countered
    0.90
    éen
    0.89
     transitioned
    0.88
    Counter
    0.85
    COUNTER
    0.84
     Transition
    0.82
    Severity
    0.82
    Activations Density 0.005%

    No Known Activations