© 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. 86988
    Prev
    Next
    INDEX
    Explanations

    Mab, Maw, Mav, Mev names

    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
     étude
    -0.89
    通用
    -0.82
     volta
    -0.72
     Angaben
    -0.68
    layah
    -0.67
    otrophic
    -0.66
    grab
    -0.66
     ruptura
    -0.66
    awesome
    -0.65
     указыва
    -0.65
    POSITIVE LOGITS
    coordinates
    0.81
     dług
    0.77
    kig
    0.75
    foglio
    0.74
    subtree
    0.73
     siker
    0.73
    オリン
    0.72
    multiline
    0.72
    マリー
    0.70
    리는
    0.70
    Activations Density 0.014%

    No Known Activations