© 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. 66158
    Prev
    Next
    INDEX
    Explanations

    problems or deficiencies

    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
     ส์
    -1.79
    ፨
    -1.57
    probably
    -1.53
     Dinas
    -1.51
    knowing
    -1.50
    巂
    -1.48
    increased
    -1.48
    relatively
    -1.47
    cots
    -1.46
    翃
    -1.45
    POSITIVE LOGITS
     or
    1.98
     because
    1.60
    0
    1.59
     или
    1.59
    2
    1.55
     while
    1.55
     there
    1.52
     if
    1.48
     excessively
    1.44
     caused
    1.37
    Activations Density 0.150%

    No Known Activations