© 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. 48738
    Prev
    Next
    INDEX
    Explanations

    education and skills development

    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
     NYPD
    -0.82
     OVERVIEW
    -0.82
    详细信息
    -0.78
     väga
    -0.78
     upfront
    -0.78
     incarcerated
    -0.78
    pement
    -0.78
    стта
    -0.77
    应对
    -0.77
     resonates
    -0.76
    POSITIVE LOGITS
     suggestions
    0.98
     school
    0.96
     pupil
    0.95
     pupils
    0.90
     Unesco
    0.88
     democratic
    0.86
     girls
    0.86
    pupil
    0.85
     girl
    0.85
     folk
    0.83
    Activations Density 0.018%

    No Known Activations