© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48138
    Prev
    Next
    INDEX
    Explanations

    "in no event"

    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
    SDR
    -0.72
     millimeters
    -0.71
     widget
    -0.69
     forklar
    -0.68
    hyp
    -0.66
    file
    -0.66
    пар
    -0.65
     virker
    -0.65
    LOG
    -0.63
     NM
    -0.63
    POSITIVE LOGITS
    ницы
    0.75
    Disposal
    0.71
     ác
    0.71
    нице
    0.66
    mtl
    0.66
    罚
    0.65
    Доб
    0.65
    theguardian
    0.65
    owią
    0.64
    ulun
    0.63
    Activations Density 0.030%

    No Known Activations