© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69901
    Prev
    Next
    INDEX
    Explanations

    python code or email headers

    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
     übrigen
    -0.73
    你说
    -0.71
    тические
    -0.68
    aras
    -0.66
     Host
    -0.66
     Stade
    -0.65
    forschung
    -0.65
    tabilidade
    -0.65
     Gospel
    -0.65
     жан
    -0.64
    POSITIVE LOGITS
    })(
    0.70
    mmings
    0.69
     Expressway
    0.66
     QtGui
    0.66
    نجليزية
    0.66
    omethane
    0.65
    冰冰
    0.65
    ⠇
    0.65
    ➡️
    0.65
    نز
    0.65
    Activations Density 0.050%

    No Known Activations