© 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. 63703
    Prev
    Next
    INDEX
    Explanations

    Cloud Training

    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
    Directeur
    -1.39
    などは
    -1.15
     špec
    -1.06
     čier
    -1.05
    Fiche
    -1.04
    がある
    -1.03
    Première
    -1.01
     chaussures
    -1.00
    Categorie
    -1.00
    Danish
    -1.00
    POSITIVE LOGITS
     body
    1.49
    Body
    1.25
    body
    1.17
    BODY
    1.03
     Body
    1.03
    header
    1.02
     header
    1.02
    To
    1.02
     When
    0.96
    Many
    0.95
    Activations Density 0.006%

    No Known Activations