© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53411
    Prev
    Next
    INDEX
    Explanations

    policies prioritizing

    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_65k_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
     provides
    0.48
     manages
    0.46
     produces
    0.46
     assesses
    0.44
     develops
    0.43
     documented
    0.43
    닮
    0.41
    ību
    0.41
     обеспечивает
    0.41
     receives
    0.41
    POSITIVE LOGITS
     Chinatown
    0.43
    카
    0.42
    블
    0.42
    Choisissez
    0.41
    બા
    0.40
    극장
    0.37
    😭
    0.37
    齙
    0.37
    ції
    0.37
     czerw
    0.37
    Activations Density 0.001%

    No Known Activations