© 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. 46140
    Prev
    Next
    INDEX
    Explanations

    introducing a list

    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
    voll
    0.77
    اء
    0.75
    ق
    0.73
    ر
    0.73
    全球
    0.71
    ع
    0.71
    h
    0.68
    ف
    0.67
    انية
    0.67
     Accidents
    0.66
    POSITIVE LOGITS
    ”
    0.78
    ется
    0.71
    ﺪ
    0.71
    "
    0.69
    ﻢ
    0.68
    ﻮ
    0.67
    ON
    0.66
     messageShow
    0.66
     आहे
    0.65
     kdo
    0.65
    Activations Density 0.001%

    No Known Activations