© 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. 34-GEMMASCOPE-RES-131K
    7. 30338
    Prev
    Next
    INDEX
    Explanations

    ready for or to

    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_34/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
     Geruch
    -1.01
     acabados
    -0.94
     gemein
    -0.93
    \
    -0.93
    s
    -0.91
    Rus
    -0.90
    ְ
    -0.89
     で
    -0.89
                        
    -0.88
     sposób
    -0.88
    POSITIVE LOGITS
     ready
    1.71
     to
    1.61
    ready
    1.55
    Ready
    1.37
    READY
    1.33
     READY
    1.30
     Ready
    1.30
     готова
    1.29
     готовы
    1.21
    onReady
    1.20
    Activations Density 0.011%

    No Known Activations