© 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. 123719
    Prev
    Next
    INDEX
    Explanations

    start checking primes

    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
    ↵
    0.55
    -
    0.52
    2
    0.52
     L
    0.46
     Pont
    0.45
     T
    0.45
     ed
    0.45
    NG
    0.45
     Ed
    0.44
     O
    0.44
    POSITIVE LOGITS
     upto
    0.58
     інших
    0.58
    ociaż
    0.56
    unehmen
    0.54
     eğer
    0.54
    خیص
    0.54
     других
    0.53
    úscula
    0.50
    䀒
    0.50
     অন্য
    0.50
    Activations Density 0.003%

    No Known Activations