© 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. 1266
    Prev
    Next
    INDEX
    Explanations

    the planet Earth

    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
    л
    0.99
    tı
    0.90
    of
    0.82
    cientes
    0.82
    де
    0.75
    кр
    0.74
    лло
    0.73
    ق
    0.73
    ٻ
    0.73
    ллі
    0.72
    POSITIVE LOGITS
     Earth
    1.18
     in
    0.88
     earth
    0.85
     the
    0.82
     Day
    0.81
    ;
    0.77
    s
    0.75
     April
    0.74
     }
    0.74
     K
    0.74
    Activations Density 0.015%

    No Known Activations