© 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. 123726
    Prev
    Next
    INDEX
    Explanations

    early stages of growth

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

    words describing new or early-stage entities or conditions, such as "nascent," "fledgling," "incipient," "embryonic," and "burgeoning."

    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
    ſu
    -2.41
     mentales
    -2.14
    ꜆
    -2.09
     uren
    -2.06
     globales
    -2.06
     orale
    -2.06
    鑁
    -2.00
     satisfaire
    -1.99
     reise
    -1.98
     saluti
    -1.98
    POSITIVE LOGITS
    ’
    2.75
     as
    2.33
    t
    2.30
    In
    2.03
     on
    1.97
     Since
    1.95
    ;
    1.89
     This
    1.88
     —
    1.87
    [
    1.84
    Activations Density 0.020%

    No Known Activations