© 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. 34-GEMMASCOPE-RES-131K
    7. 98897
    Prev
    Next
    INDEX
    Explanations

    warnings and mentions

    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
     alebo
    -1.08
     проверить
    -0.85
     posting
    -0.85
     тысяч
    -0.85
     Chip
    -0.83
    ...@
    -0.81
     проверки
    -0.80
    acky
    -0.78
    语文
    -0.78
     результате
    -0.77
    POSITIVE LOGITS
     mention
    1.63
     mentions
    1.53
    Mentions
    1.45
     mentioned
    1.42
     упомина
    1.32
    mention
    1.27
    mentioned
    1.20
    Mention
    1.19
     Mention
    1.16
    提及
    1.16
    Activations Density 0.012%

    No Known Activations