© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59261
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
     After
    -1.91
    了不少
    -1.76
    ጺ
    -1.74
     all
    -1.67
     add
    -1.62
    了些
    -1.62
    </i>
    -1.61
     Institutionen
    -1.59
    囯
    -1.55
    Тогда
    -1.55
    POSITIVE LOGITS
    錞
    1.80
    does
    1.69
     verbre
    1.68
    ⤞
    1.67
     två
    1.60
     embarazada
    1.58
     ljudi
    1.54
    (‘
    1.52
     puramente
    1.51
     entrando
    1.45
    Activations Density 0.004%

    No Known Activations