© 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. 34735
    Prev
    Next
    INDEX
    Explanations

    No. or Nos. following case 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
    oneph
    -0.75
    ≠
    -0.74
    Durata
    -0.74
     Taro
    -0.73
    hörigen
    -0.72
    ilov
    -0.72
    伅
    -0.71
    icago
    -0.70
    yaar
    -0.69
     hiker
    -0.68
    POSITIVE LOGITS
     provincias
    0.68
    itat
    0.68
    Kelebihan
    0.67
    二日
    0.66
     ACC
    0.65
     España
    0.65
     Gathering
    0.65
    alternatives
    0.65
    前世
    0.64
    utor
    0.63
    Activations Density 0.109%

    No Known Activations