© 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. 31-GEMMASCOPE-2-RES-262K
    7. 44551
    Prev
    Next
    INDEX
    Explanations

    read the room

    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_31_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
    im
    0.74
    ’
    0.73
    ani
    0.71
     хорошее
    0.71
    u
    0.70
    لی
    0.66
    !’
    0.63
    rt
    0.62
    قب
    0.62
    inę
    0.62
    POSITIVE LOGITS
     read
    1.05
    讀
    0.84
     Read
    0.81
    读
    0.81
     읽
    0.77
     READ
    0.75
     Baca
    0.75
     aloud
    0.74
     读取
    0.74
    读取
    0.73
    Activations Density 0.050%

    No Known Activations