© 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. 48210
    Prev
    Next
    INDEX
    Explanations

    oil and gas companies

    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
     или
    -1.66
    -
    -1.63
     muñeco
    -1.60
    はもう
    -1.59
    躄
    -1.55
     affirme
    -1.51
     $
    -1.45
    钐
    -1.41
    "[
    -1.41
    不得不
    -1.40
    POSITIVE LOGITS
    ㈯
    1.59
    鼇
    1.53
    」。
    1.51
    ፧
    1.51
     що
    1.50
     those
    1.50
    鐿
    1.49
    🪣
    1.47
    ции
    1.42
    聾
    1.42
    Activations Density 0.006%

    No Known Activations