© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136635
    Prev
    Next
    INDEX
    Explanations

    ethical and defensive security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     context
    0.45
    www
    0.45
    $$
    0.44
     \{
    0.43
    สิ้น
    0.42
    ка
    0.42
     stressful
    0.41
     www
    0.41
    ит
    0.40
    ||
    0.40
    POSITIVE LOGITS
     Cez
    0.53
    enamefont
    0.52
     vélo
    0.50
     Fukuoka
    0.49
     traigo
    0.49
     użyt
    0.48
    közi
    0.48
     privée
    0.48
    produkte
    0.48
    pellier
    0.48
    Activations Density 0.003%

    No Known Activations