© 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. 128821
    Prev
    Next
    INDEX
    Explanations

    workshop on

    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
    埽
    -2.97
    琑
    -2.88
     zoude
    -2.88
    鲎
    -2.59
    缑
    -2.58
    ,"
    -2.55
    鲞
    -2.52
    栳
    -2.52
    genodigd
    -2.52
     obligatory
    -2.52
    POSITIVE LOGITS
     Then
    2.91
    媄
    2.64
     Following
    2.45
    
    2.45
    .
    2.45
     Numerous
    2.42
     Normally
    2.39
     Currently
    2.38
    It
    2.38
     Тогда
    2.36
    Activations Density 0.004%

    No Known Activations