© 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. 22-GEMMASCOPE-RES-131K
    7. 25299
    Prev
    Next
    INDEX
    Explanations

    for loop structures

    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_22/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
     just
    -1.73
     even
    -1.69
     three
    -1.54
     to
    -1.46
     way
    -1.42
     most
    -1.41
    ]
    -1.41
     two
    -1.40
     first
    -1.38
    叡
    -1.34
    POSITIVE LOGITS
    (
    1.48
    ي
    1.37
     erheblich
    1.30
    ífer
    1.27
     améliorer
    1.27
    店頭
    1.25
    割と
    1.23
     ซึ่ง
    1.22
     sichtbar
    1.22
    ፲
    1.21
    Activations Density 0.002%

    No Known Activations