© 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. 10-GEMMASCOPE-RES-131K
    7. 85957
    Prev
    Next
    INDEX
    Explanations

    it started when

    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_10/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
     the
    -1.95
     another
    -1.60
     raggiungere
    -1.41
     entrare
    -1.41
     söyledi
    -1.40
     scrivere
    -1.38
     scegliere
    -1.37
     tornare
    -1.37
     certain
    -1.34
    ονται
    -1.34
    POSITIVE LOGITS
     of
    1.52
    écial
    1.28
     lópez
    1.16
    格子
    1.15
     engraving
    1.15
    zeichnung
    1.13
    の人生
    1.12
    禄
    1.11
    UTTON
    1.11
    tedrale
    1.10
    Activations Density 0.074%

    No Known Activations