Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18970
    Prev
    Next
    INDEX
    Explanations

    countries after "of"

    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
    ერთი
    0.52
    ีย์
    0.44
    硫酸
    0.44
    اے
    0.42
    夂
    0.42
    خ
    0.42
     suscit
    0.40
    上記の
    0.39
    心思
    0.39
    Así
    0.39
    POSITIVE LOGITS
     Australia
    0.68
    '
    0.64
     America
    0.62
     Colombia
    0.59
     Hungary
    0.56
     India
    0.55
     Mongolia
    0.55
     України
    0.55
     Nigeria
    0.54
     Albania
    0.54
    Activations Density 0.027%

    No Known Activations