© 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. 53419
    Prev
    Next
    INDEX
    Explanations

    resignation and opportunities

    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
     democracia
    0.48
    道歉
    0.48
     dignidad
    0.46
    🇭
    0.46
    Corruption
    0.45
     патри
    0.45
    螻
    0.45
    Platz
    0.44
     ciudadanía
    0.44
    犧
    0.44
    POSITIVE LOGITS
     playroom
    0.50
     remote
    0.46
     research
    0.46
     Remote
    0.46
     rapidly
    0.45
     pinpoint
    0.45
     internet
    0.44
     Office
    0.44
     Elf
    0.44
     Northwest
    0.44
    Activations Density 0.002%

    No Known Activations