© 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. 5743
    Prev
    Next
    INDEX
    Explanations

    infrastructure, managing, hosting

    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
     citizenship
    0.49
     permittivity
    0.47
     sugar
    0.45
    ף
    0.43
     carbohydrates
    0.43
     lambda
    0.43
    lambda
    0.42
    なくて
    0.42
    ούς
    0.42
     porcelain
    0.41
    POSITIVE LOGITS
    imar
    0.52
    అ
    0.48
    icuously
    0.45
     modalCard
    0.45
     بعد
    0.45
     или
    0.44
     अनुमान
    0.44
     अंदा
    0.44
    им
    0.44
    ynam
    0.44
    Activations Density 0.001%

    No Known Activations