© 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. 34-GEMMASCOPE-RES-131K
    7. 109933
    Prev
    Next
    INDEX
    Explanations

    Christmas lights, lightsaber battles

    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_34/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
     steels
    -0.90
    TAWA
    -0.80
    mosaic
    -0.77
    鹃
    -0.75
     الصيف
    -0.75
    ární
    -0.73
    łby
    -0.73
    ֶּ
    -0.73
    gnar
    -0.72
    Datasource
    -0.71
    POSITIVE LOGITS
     decoder
    1.18
     realism
    1.02
     realistic
    0.92
    decoder
    0.92
    Sound
    0.90
     模型
    0.89
    模型
    0.89
     sound
    0.89
     Decoder
    0.85
    Decoder
    0.84
    Activations Density 0.007%

    No Known Activations