© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77160
    Prev
    Next
    INDEX
    Explanations

    text operations

    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
     format
    -0.84
     needs
    -0.79
    formato
    -0.78
    فتح
    -0.75
    寐
    -0.74
    mata
    -0.73
     size
    -0.73
    切る
    -0.72
     propias
    -0.71
     eigenen
    -0.70
    POSITIVE LOGITS
     text
    2.17
    getText
    1.75
    Text
    1.70
     Text
    1.68
    text
    1.53
     getText
    1.53
     текст
    1.45
     тек
    1.33
     texts
    1.30
     TEXT
    1.28
    Activations Density 0.006%

    No Known Activations