© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 681
    Prev
    Next
    INDEX
    Explanations

    horizontal orientation

    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
     The
    -3.11
    栳
    -2.83
    跄
    -2.83
    ’
    -2.70
    鉿
    -2.64
     torner
    -2.56
     dangereux
    -2.56
     AppCompatTheme
    -2.45
    ⢊
    -2.44
    笅
    -2.42
    POSITIVE LOGITS
    骝
    3.45
    ଃ
    2.97
    只剩
    2.94
    媗
    2.94
    "
    2.92
    鈊
    2.92
    ︲
    2.89
    本章
    2.84
    下一篇
    2.81
    ization
    2.80
    Activations Density 0.010%

    No Known Activations