© 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. 72416
    Prev
    Next
    INDEX
    Explanations

    privilege escalation and access

    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
    
    -2.63
     we
    -2.53
    ꜆
    -2.41
    鑁
    -2.34
     którzy
    -2.23
    瓩
    -2.20
     proficient
    -2.20
    ⸢
    -2.19
    甍
    -2.14
    </i>
    -2.13
    POSITIVE LOGITS
    Quite
    2.63
    While
    2.53
    Following
    2.50
     после
    2.42
     Following
    2.39
    According
    2.31
     Quite
    2.27
          
    2.25
     There
    2.22
     GREAT
    2.20
    Activations Density 0.002%

    No Known Activations