© 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. 65258
    Prev
    Next
    INDEX
    Explanations

    photon emission

    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
     they
    -3.89
    ’
    -3.22
    ↵
    -3.05
     dritte
    -2.81
    柺
    -2.73
     wenige
    -2.59
     offizielle
    -2.47
     letzte
    -2.42
    푣
    -2.31
     vollständige
    -2.30
    POSITIVE LOGITS
    🫃
    3.30
    ൎ
    3.20
    媖
    2.91
    ፨
    2.66
    呖
    2.66
    ꙰
    2.56
     ());
    2.52
    нутрен
    2.52
    служба
    2.50
    Doesn
    2.47
    Activations Density 0.001%

    No Known Activations