© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47558
    Prev
    Next
    INDEX
    Explanations

    Q: or Measurements of

    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
    猬
    -0.81
     Castro
    -0.79
     допусти
    -0.75
     Mario
    -0.72
    chauer
    -0.71
    纪录
    -0.70
    ränk
    -0.70
    ゾート
    -0.69
     Links
    -0.69
     immedi
    -0.68
    POSITIVE LOGITS
    enapa
    0.79
     羽
    0.74
    nasium
    0.74
    ığınız
    0.73
    δας
    0.73
     Asbury
    0.73
     refills
    0.73
     Quincy
    0.72
    fontein
    0.72
     bing
    0.72
    Activations Density 0.004%

    No Known Activations