© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118834
    Prev
    Next
    INDEX
    Explanations

    friendly, compatible, ready, capable

    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
     następujące
    -0.91
     intéressante
    -0.90
     basée
    -0.87
     jakość
    -0.82
     personnalisée
    -0.80
     phénom
    -0.80
     beträ
    -0.76
    ritzau
    -0.76
    に戻る
    -0.75
     mußten
    -0.74
    POSITIVE LOGITS
     ready
    3.61
     compatible
    3.36
    ready
    3.16
     friendly
    2.88
    Ready
    2.80
     Ready
    2.72
     capable
    2.64
    READY
    2.64
     worthy
    2.53
    compatible
    2.48
    Activations Density 0.167%

    No Known Activations