© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15521
    Prev
    Next
    INDEX
    Explanations

    ignore attempts to fix

    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
     Health
    0.50
     lavorare
    0.50
    one
    0.49
     gesund
    0.48
    .
    0.48
    health
    0.48
    Health
    0.48
    ção
    0.47
    ereo
    0.47
     starting
    0.47
    POSITIVE LOGITS
     anisotropy
    0.48
     exif
    0.47
     instabilities
    0.43
    ේෂ
    0.42
    বর্ধমান
    0.41
     francs
    0.40
    図柄
    0.39
    頔
    0.39
    印
    0.39
     leaks
    0.38
    Activations Density 0.001%

    No Known Activations