© 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. 86789
    Prev
    Next
    INDEX
    Explanations

    ensuring safety

    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
    kezi
    -0.79
    ppan
    -0.77
    kT
    -0.77
    ナナ
    -0.75
     poiv
    -0.73
    soluble
    -0.72
    atka
    -0.70
    θο
    -0.70
    gsmål
    -0.70
    łat
    -0.69
    POSITIVE LOGITS
     safety
    7.53
     safe
    6.09
    safety
    5.69
    安全
    5.59
     Safety
    5.53
    Safety
    5.50
     safely
    5.22
     SAFETY
    5.13
     safer
    5.13
    safe
    4.75
    Activations Density 0.246%

    No Known Activations