© 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. 57691
    Prev
    Next
    INDEX
    Explanations

    editors and editorials

    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
    Suivez
    -0.81
    恐怕
    -0.79
    áneas
    -0.79
    Contactez
    -0.79
    gnon
    -0.76
    ataa
    -0.76
    arts
    -0.74
    adog
    -0.73
    ఇ
    -0.72
    IntOverflow
    -0.72
    POSITIVE LOGITS
     editorial
    3.64
    Editorial
    3.06
     Editorial
    3.02
    editorial
    2.88
     EDITORIAL
    2.36
    EDITORIAL
    2.13
     editor
    2.02
     Editor
    1.77
     editors
    1.70
    editor
    1.59
    Activations Density 0.044%

    No Known Activations