© 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-65K
    7. 52986
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    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_65k_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
     capabilities
    0.40
    SelectionSet
    0.36
     numeric
    0.35
     Groundwater
    0.35
     个
    0.35
     Quân
    0.34
    ў
    0.34
    处的
    0.33
    ख़
    0.33
     suất
    0.33
    POSITIVE LOGITS
    アメリカ
    0.58
    美國
    0.54
    Switzerland
    0.49
     США
    0.49
    社會
    0.49
    México
    0.49
     Amerika
    0.47
    Amerika
    0.47
     アメリカ
    0.46
    美国的
    0.45
    Activations Density 0.001%

    No Known Activations