© 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. 22-GEMMASCOPE-RES-131K
    7. 70429
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ਗ਼
    -1.70
    »،
    -1.65
    んですよ
    -1.58
    ほら
    -1.46
    感じで
    -1.45
    €“
    -1.44
    に入れ
    -1.42
    んですよね
    -1.41
     rédu
    -1.41
    ことが多い
    -1.35
    POSITIVE LOGITS
    しかし
    1.52
    <bos>
    1.22
    その
    1.21
    ffè
    1.20
    そのため
    1.17
    توضیحات
    1.16
    دانلود
    1.13
    視野
    1.13
    CCIÓN
    1.13
     الشرطة
    1.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.