© 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. 50346
    Prev
    Next
    INDEX
    Explanations

    Talking Point, Mouse models

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

    timestamps, dates, and numerical formatting in media transcripts.

    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
     television
    -0.84
    テレビ
    -0.84
    Videos
    -0.80
    ɐ
    -0.80
    王妃
    -0.79
     lyder
    -0.79
    商品説明
    -0.78
     pleadings
    -0.77
     televisions
    -0.77
    𝟔
    -0.76
    POSITIVE LOGITS
     producer
    1.35
     listeners
    1.33
     host
    1.24
     Produced
    1.23
     producers
    1.20
     Producer
    1.19
     guests
    1.14
     listener
    1.13
    Producer
    1.08
    Segment
    1.03
    Activations Density 0.057%

    No Known Activations