© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43474
    Prev
    Next
    INDEX
    Explanations

    abbreviation for amino acids

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

    the letters "aa" in text, particularly when they appear in identifiers, variable names, or codes.

    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
    ة
    -2.70
     is
    -2.61
    <em>
    -2.55
     of
    -2.50
     speziellen
    -2.34
    dreamstime
    -2.22
     zwölf
    -2.22
    ommation
    -2.19
     einzigartigen
    -2.17
    ing
    -2.09
    POSITIVE LOGITS
    ERS
    2.44
    鯷
    2.41
    people
    2.41
    section
    2.33
    ⇩
    2.27
    ❢
    2.25
     uur
    2.20
    s
    2.17
    IN
    2.13
    )".
    2.13
    Activations Density 0.003%

    No Known Activations