© 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. 118626
    Prev
    Next
    INDEX
    Explanations

    soft skills and competencies

    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
    BindingSource
    -0.82
     Rodrigues
    -0.79
     RIPRODUZIONE
    -0.77
     PRINCIPLES
    -0.75
    🐔
    -0.73
    🏘
    -0.73
     MINOR
    -0.72
    isUser
    -0.71
     Dolby
    -0.71
     studier
    -0.70
    POSITIVE LOGITS
     skills
    2.58
     soft
    2.36
     competencies
    2.19
     skill
    2.06
    soft
    2.00
    skills
    1.81
    Soft
    1.73
     Soft
    1.67
     Skills
    1.66
     compet
    1.64
    Activations Density 0.032%

    No Known Activations