© 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. 120003
    Prev
    Next
    INDEX
    Explanations

    biological and technical descriptions

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

    transition words or phrases like "for", "by", "in", or "is" that connect ideas in academic or technical writing.

    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
     there
    -1.71
    F
    -1.41
     members
    -1.27
    ↵
    -1.27
     make
    -1.27
    ă
    -1.25
    ;
    -1.24
    -
    -1.23
    O
    -1.22
    K
    -1.22
    POSITIVE LOGITS
     publicó
    1.41
     secrétaire
    1.41
    raje
    1.38
    adla
    1.38
     persoalan
    1.36
    président
    1.35
     personagens
    1.32
     journaliste
    1.31
     tantangan
    1.31
     différents
    1.30
    Activations Density 0.451%

    No Known Activations