© 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. 119710
    Prev
    Next
    INDEX
    Explanations

    understanding peptide

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

    section headers and formatting in academic or scientific documents.

    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
    ing
    -2.13
    ⢓
    -2.03
     hunde
    -2.03
    媖
    -2.00
    ة
    -1.95
    蹌
    -1.92
     menggunakan
    -1.89
     retrô
    -1.88
    ’:
    -1.87
    挲
    -1.86
    POSITIVE LOGITS
    ();
    2.34
    铩
    2.20
    s
    2.14
    !
    2.13
    她
    2.09
    of
    2.08
    他
    1.98
    ピアノ
    1.98
     birkaç
    1.92
    m
    1.89
    Activations Density 0.000%

    No Known Activations