© 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. 98820
    Prev
    Next
    INDEX
    Explanations

    seasonal variation

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical notation and programming-related content in technical questions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Reproduction
    -0.84
    igin
    -0.79
     fédéral
    -0.76
    displacement
    -0.75
    ulatum
    -0.74
     название
    -0.74
     บ
    -0.73
    жил
    -0.73
     topping
    -0.71
    Reproduction
    -0.71
    POSITIVE LOGITS
     reshape
    2.58
    reshape
    2.58
     shape
    1.52
    RESH
    1.44
     shaping
    1.43
     shaped
    1.37
    haping
    1.28
     Shaping
    1.26
     restructuring
    1.19
    の形
    1.17
    Activations Density 0.009%

    No Known Activations