© 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. 10-GEMMASCOPE-RES-131K
    7. 39028
    Prev
    Next
    INDEX
    Explanations

    to destroy

    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_10/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
    跸
    -1.82
     ʻ
    -1.78
    rdoba
    -1.75
     ſch
    -1.69
     merav
    -1.65
    لوار
    -1.65
    liſh
    -1.63
    赑
    -1.63
    дии
    -1.63
    iziert
    -1.63
    POSITIVE LOGITS
    ↵
    2.09
     whereas
    1.59
     it
    1.56
     and
    1.53
     Businesses
    1.44
    .
    1.41
    {
    1.39
    jauh
    1.33
     Zerst
    1.31
    ipfel
    1.30
    Activations Density 0.038%

    No Known Activations