© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4183
    Prev
    Next
    INDEX
    Explanations

    data privacy concerns

    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
     GoObject
    0.57
     meditative
    0.55
     decad
    0.54
     nymphs
    0.54
     grinning
    0.54
    Ⲁ
    0.52
     foliis
    0.52
     atmosfé
    0.52
    绚
    0.52
     chromatic
    0.50
    POSITIVE LOGITS
     Privacy
    1.75
     privacy
    1.63
    Privacy
    1.55
    privacy
    1.49
     Datenschutz
    1.36
     GDPR
    1.31
    隐私
    1.31
     privacidade
    1.12
     गोपनीयता
    1.12
     privacidad
    1.11
    Activations Density 0.203%

    No Known Activations