© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91777
    Prev
    Next
    INDEX
    Explanations

    editors and newsrooms

    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
    fahrzeug
    -0.73
     Kraft
    -0.73
    יפה
    -0.71
     kitap
    -0.71
     глава
    -0.70
     trouverez
    -0.69
     المجلس
    -0.68
     listView
    -0.68
    룰
    -0.68
    referral
    -0.67
    POSITIVE LOGITS
     editorial
    2.50
     редак
    2.28
     editors
    2.19
     editor
    2.00
     redacción
    1.84
     Editor
    1.80
    editorial
    1.80
    editor
    1.73
    Editor
    1.73
     Editorial
    1.72
    Activations Density 0.031%

    No Known Activations