© 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. 19932
    Prev
    Next
    INDEX
    Explanations

    common ground, land, language, good

    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
     arent
    1.09
    对
    0.98
    在
    0.98
     errado
    0.97
    我们
    0.96
     viaj
    0.92
     oka
    0.91
     acorde
    0.90
     mecánica
    0.90
    يع
    0.89
    POSITIVE LOGITS
    м
    1.57
    م
    1.51
    ம்
    1.44
    ות
    1.40
    ти
    1.30
    ం
    1.20
    ം
    1.16
    ان
    1.11
    ित
    1.07
    en
    1.06
    Activations Density 0.007%

    No Known Activations