© 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. 115844
    Prev
    Next
    INDEX
    Explanations

    people places organizations followed by specifics

    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
     surla
    -1.28
     fera
    -1.27
     mág
    -1.20
     gioielli
    -1.19
     toca
    -1.19
     offre
    -1.17
     situe
    -1.17
     remet
    -1.16
     essentiel
    -1.16
     agora
    -1.16
    POSITIVE LOGITS
     opinião
    1.11
    Appellants
    1.05
     previsão
    1.01
     afore
    0.99
    kách
    0.98
    Atsauces
    0.95
     intenção
    0.94
     japanese
    0.92
     derselbe
    0.92
     cauza
    0.91
    Activations Density 0.242%

    No Known Activations