© 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. 50692
    Prev
    Next
    INDEX
    Explanations

    changes and their consequences

    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
     prohibitions
    0.45
     approvals
    0.44
     standings
    0.42
     图片
    0.42
     売
    0.41
     названия
    0.41
     Oaks
    0.40
     头
    0.40
     sales
    0.39
     “(
    0.39
    POSITIVE LOGITS
    зацию
    0.40
     காணப்படும்
    0.39
     фонда
    0.39
    quiet
    0.39
    čių
    0.39
    ப்படாத
    0.39
    ப்பட்டி
    0.39
    expérience
    0.38
    感动
    0.38
    olysis
    0.38
    Activations Density 0.001%

    No Known Activations