© 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-262K
    7. 28080
    Prev
    Next
    INDEX
    Explanations

    Antarctica and arctic

    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_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
     =",
    0.69
     taco
    0.68
     ware
    0.66
     scallops
    0.66
     skater
    0.66
     waivers
    0.66
     publicaciones
    0.65
     +/-
    0.64
     waterslide
    0.64
     burrito
    0.64
    POSITIVE LOGITS
    int
    0.85
    um
    0.82
    AM
    0.81
     Antarctica
    0.75
    MS
    0.74
    EC
    0.73
    AT
    0.71
    om
    0.70
    A
    0.70
    Un
    0.69
    Activations Density 0.001%

    No Known Activations