© 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. 57253
    Prev
    Next
    INDEX
    Explanations

    code snippets or comments start

    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
     Seder
    -0.79
     ಜ
    -0.78
    맨
    -0.72
    Lerp
    -0.71
     ویت
    -0.70
    Artificial
    -0.69
    Cheese
    -0.69
    advertisement
    -0.68
    ulkan
    -0.67
     núcleo
    -0.66
    POSITIVE LOGITS
    readable
    0.69
     guile
    0.67
     meny
    0.67
    extendable
    0.66
    ENST
    0.65
     Raad
    0.65
     εκεί
    0.64
    熊
    0.64
     стъ
    0.64
     жени
    0.63
    Activations Density 0.058%

    No Known Activations