© 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. 16-GEMMASCOPE-2-RES-65K
    7. 246
    Prev
    Next
    INDEX
    Explanations

    bonus gold

    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_16_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
    vo
    0.50
    vez
    0.50
    vée
    0.50
    voer
    0.49
    0
    0.49
    portfolio
    0.48
    vad
    0.47
    vál
    0.47
    voja
    0.46
    zeg
    0.46
    POSITIVE LOGITS
     MEETING
    0.50
     Glossary
    0.49
    ס
    0.49
    Л
    0.48
    ப
    0.48
     evento
    0.47
    岨
    0.47
     Vitt
    0.46
     이벤트
    0.46
    イチ
    0.46
    Activations Density 0.000%

    No Known Activations