© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44551
    Prev
    Next
    INDEX
    Explanations

    reads - IF

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inę
    0.67
    لی
    0.66
    ani
    0.65
    u
    0.64
    im
    0.63
    ק
    0.60
     اکبر
    0.59
    कार
    0.59
    ذیر
    0.59
    akai
    0.58
    POSITIVE LOGITS
     read
    1.22
    讀
    1.09
    读
    1.08
     读取
    1.07
     READ
    1.05
     Read
    1.04
    读取
    1.00
     Reading
    0.96
     읽
    0.95
     อ่าน
    0.91
    Activations Density 0.045%

    No Known Activations