© 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. 23661
    Prev
    Next
    INDEX
    Explanations

    code snippets and versioning

    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
    Mais
    -0.71
    槻
    -0.71
    berti
    -0.70
    嫌い
    -0.70
    вать
    -0.69
     Probe
    -0.69
    yonel
    -0.69
     selbst
    -0.68
     Date
    -0.67
     ز
    -0.67
    POSITIVE LOGITS
     compacted
    0.68
     blauw
    0.65
     मिले
    0.65
    дини
    0.64
    Attach
    0.63
    담
    0.63
     Parke
    0.63
    rativa
    0.61
    aryn
    0.61
    oore
    0.61
    Activations Density 0.051%

    No Known Activations