© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48372
    Prev
    Next
    INDEX
    Explanations

    should not be

    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
    ⎔
    -2.66
    龉
    -2.63
    沨
    -2.38
     шапка
    -2.34
     them
    -2.25
     potrebné
    -2.20
     kurzem
    -2.16
    ᆞ
    -2.16
     comanda
    -2.16
    かもし
    -2.16
    POSITIVE LOGITS
    (
    3.67
    '
    3.22
    t
    2.92
    j
    2.55
    ar
    2.41
    Is
    2.39
    </td>
    2.38
    il
    2.36
    On
    2.33
    Do
    2.23
    Activations Density 0.012%

    No Known Activations