© 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. 102376
    Prev
    Next
    INDEX
    Explanations

    you begin

    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
    ↵
    -3.13
     as
    -2.39
            
    -2.39
    </strong>
    -2.31
     or
    -2.22
     There
    -2.17
     not
    -2.16
    </i>
    -2.16
     It
    -2.13
              
    -2.11
    POSITIVE LOGITS
    眎
    2.64
    鹇
    2.64
     etek
    2.56
    
    2.50
    Ꮔ
    2.50
    蔸
    2.48
     diki
    2.48
     helg
    2.44
    幛
    2.44
     groen
    2.41
    Activations Density 0.005%

    No Known Activations