© 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. 68875
    Prev
    Next
    INDEX
    Explanations

    dodecylbenzene sulfonate / sulfate

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

    chemical and biochemical compounds or technical abbreviations, particularly those with multiple syllables.

    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_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
    easily
    -2.73
    鑁
    -2.61
    somewhat
    -2.20
     º
    -2.19
    岽
    -2.16
    stupid
    -2.14
    屙
    -2.06
    اں
    -2.05
    蟶
    -2.02
    sandalia
    -2.00
    POSITIVE LOGITS
     are
    2.33
    ли
    2.23
     unsere
    2.20
    ֟
    2.19
    聳
    2.17
                    
    2.16
    嵎
    2.16
    item
    2.11
    the
    2.08
    li
    2.06
    Activations Density 0.050%

    No Known Activations