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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4055
    Prev
    Next
    INDEX
    Explanations

    skill or skilled phrases

    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
    无线
    -0.90
    減
    -0.90
    fusc
    -0.82
    Wert
    -0.79
     части
    -0.79
     £
    -0.79
    Louisville
    -0.79
     vapor
    -0.78
    Ż
    -0.77
     reps
    -0.75
    POSITIVE LOGITS
     skill
    1.37
    Skill
    1.20
    skill
    1.16
     Skill
    1.11
     skilful
    0.96
     skills
    0.96
    skills
    0.94
     fiches
    0.92
     skillful
    0.91
    skilled
    0.90
    Activations Density 0.007%

    No Known Activations