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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130557
    Prev
    Next
    INDEX
    Explanations

    comment markers (`/*` or `/**`)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </b>
    -2.61
    ⤥
    -2.41
    หรือ
    -2.30
     друзьями
    -2.28
    啖
    -2.08
     může
    -2.06
     $
    -2.00
     '
    -1.99
     añade
    -1.98
    みたい
    -1.98
    POSITIVE LOGITS
    "
    3.30
    ."));
    2.36
    埽
    2.20
     prochaines
    2.16
    The
    2.16
    et
    2.09
     Islas
    2.08
    􏰀
    2.06
     雙
    2.05
    
    2.03
    Activations Density 0.002%

    No Known Activations