© 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. 4306
    Prev
    Next
    INDEX
    Explanations

    skills, accomplishments, experience

    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
    Advice
    -0.88
     консульта
    -0.83
    zionalità
    -0.80
    öhnen
    -0.79
    дми
    -0.78
    ļa
    -0.78
     статус
    -0.77
    ;';
    -0.76
    лость
    -0.75
     apparence
    -0.74
    POSITIVE LOGITS
     relevant
    1.45
     skills
    1.34
     demonstrate
    1.33
     demonstrated
    1.30
     related
    1.30
     your
    1.30
     previous
    1.26
     accomplishments
    1.24
     applicant
    1.19
     experience
    1.16
    Activations Density 0.016%

    No Known Activations