© 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. 622
    Prev
    Next
    INDEX
    Explanations

    HTML ul tags

    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
    و
    0.92
    ຜະລິດຕະພັນ
    0.73
    프트
    0.72
    ک
    0.72
    아
    0.69
    ೆ
    0.66
    𐰣
    0.66
    Ꮕ
    0.65
    Пере
    0.64
    ް
    0.64
    POSITIVE LOGITS
     ul
    0.80
     Ul
    0.71
     UL
    0.71
    ul
    0.70
    un
    0.66
    tti
    0.61
     YOLO
    0.61
    ía
    0.60
    ibilit
    0.59
     ILO
    0.59
    Activations Density 0.001%

    No Known Activations