© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 10053
    Prev
    Next
    INDEX
    Explanations

    South African places

    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_53_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
    ྞ
    0.47
     interstit
    0.45
     Descriptive
    0.44
     Metadata
    0.42
     ভিয়েতনাম
    0.41
     expts
    0.40
     সংস্কৃতি
    0.40
     karm
    0.40
     균
    0.40
     epigen
    0.39
    POSITIVE LOGITS
     Pretoria
    1.06
     Gauteng
    1.02
     Johannesburg
    1.00
    Johannes
    0.96
     Bloem
    0.90
     Transvaal
    0.82
     Durban
    0.77
     KwaZulu
    0.76
     Tsh
    0.74
     Sow
    0.71
    Activations Density 0.002%

    No Known Activations