© 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. 10-GEMMASCOPE-RES-131K
    7. 119968
    Prev
    Next
    INDEX
    Explanations

    `x` and `y` coordinates or variables

    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
     and
    -2.81
     or
    -2.44
     from
    -2.05
     as
    -1.74
     because
    -1.72
     if
    -1.66
     at
    -1.65
     during
    -1.52
     before
    -1.50
     amid
    -1.50
    POSITIVE LOGITS
    opies
    1.79
    ícias
    1.62
     verwendeten
    1.51
    Mengapa
    1.49
    asties
    1.48
    呿
    1.48
    
    1.47
    ㉕
    1.45
    enie
    1.45
    美味しかった
    1.40
    Activations Density 0.056%

    No Known Activations