© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63171
    Prev
    Next
    INDEX
    Explanations

    misunderstanding, dives down

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

    list structure and delimiters

    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
    Negative Logits
    getRadius
    0.54
    ʣ
    0.52
    ),]),
    0.51
    arsipkan
    0.50
     создан
    0.48
    nCurr
    0.48
    到处
    0.47
    飡
    0.47
    ليو
    0.47
    轺
    0.46
    POSITIVE LOGITS
     gaze
    0.47
    REAM
    0.46
     pack
    0.43
     догово
    0.42
     socially
    0.41
    1
    0.41
    </strong>
    0.40
     MAKE
    0.40
    omone
    0.40
     set
    0.40
    Activations Density 0.000%

    No Known Activations