© 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. 66010
    Prev
    Next
    INDEX
    Explanations

    Network changes or Cashbox magazine

    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
     Dune
    -0.79
     grip
    -0.76
     बीच
    -0.73
    大好きな
    -0.70
     Tyres
    -0.69
    kadang
    -0.69
     Lég
    -0.68
    Somehow
    -0.68
    Σε
    -0.67
    ĕ
    -0.67
    POSITIVE LOGITS
    ITIONAL
    0.93
     Soccerway
    0.86
    λια
    0.82
    gorithm
    0.80
    toxicity
    0.77
     ثبت
    0.77
    的目光
    0.76
     Watt
    0.75
    silla
    0.75
     ----
    0.74
    Activations Density 0.008%

    No Known Activations