© 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. 4428
    Prev
    Next
    INDEX
    Explanations

    our + noun/adjective

    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
    ل
    1.69
    ת
    1.54
    त
    1.47
    ко
    1.39
    ت
    1.25
     يك
    1.24
    ي
    1.24
    Ре
    1.21
    يح
    1.21
    ди
    1.20
    POSITIVE LOGITS
    5
    1.17
    ain
    1.05
    4
    0.99
    ่า
    0.96
    EV
    0.95
    ELL
    0.91
    ara
    0.91
    ied
    0.90
    ude
    0.89
    hi
    0.89
    Activations Density 0.568%

    No Known Activations