© 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. 112581
    Prev
    Next
    INDEX
    Explanations

    workshops and making places

    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
    
    -2.50
     zoude
    -2.38
    
    -2.33
    罽
    -2.33
    縯
    -2.23
    驺
    -2.23
    felpa
    -2.17
    鲞
    -2.06
    猡
    -2.02
    
    -2.00
    POSITIVE LOGITS
     If
    2.52
    ?”
    2.34
    If
    2.31
    It
    2.19
    I
    2.11
    当然
    2.08
    L
    2.06
    While
    2.05
     Any
    2.02
     When
    2.00
    Activations Density 0.013%

    No Known Activations