© 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. 93536
    Prev
    Next
    INDEX
    Explanations

    securities and safe financial language

    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
    ciencia
    -0.79
    говой
    -0.74
    нні
    -0.72
    淪
    -0.72
     カタ
    -0.71
     سوريا
    -0.70
     instituições
    -0.70
     références
    -0.70
     Oversight
    -0.70
    trophic
    -0.69
    POSITIVE LOGITS
     safe
    2.02
    safe
    1.69
     Safe
    1.56
    Safe
    1.45
     SAFE
    1.27
     безопас
    1.16
    SAFE
    1.12
     saf
    1.03
     Securities
    0.98
     securities
    0.95
    Activations Density 0.016%

    No Known Activations