© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38675
    Prev
    Next
    INDEX
    Explanations

    safe or secure followed by word

    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
     faldas
    -1.39
     ANOTHER
    -1.34
     dificultad
    -1.30
     HOW
    -1.28
     muñecas
    -1.27
     THERE
    -1.27
     színes
    -1.25
     verdaderas
    -1.25
     meest
    -1.24
    镠
    -1.23
    POSITIVE LOGITS
     changes
    1.34
    ruckt
    1.23
     safe
    1.23
     will
    1.18
     rito
    1.17
    (
    1.16
    prägt
    1.15
     conversations
    1.13
     changed
    1.12
     Olímp
    1.10
    Activations Density 0.108%

    No Known Activations