© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12580
    Prev
    Next
    INDEX
    Explanations

    plant family and species

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

    botanical terminology related to plant taxonomy and families, particularly suffixes like "ceae" and "aceae" in plant family names.

    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_22/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
     médec
    -1.49
     asesinato
    -1.47
     médicaments
    -1.41
    PhysRevD
    -1.34
    ciclopedia
    -1.26
     latihan
    -1.23
     trajets
    -1.23
     бое
    -1.23
     bienfaits
    -1.22
     isolada
    -1.22
    POSITIVE LOGITS
     النبات
    1.34
     on
    1.33
    ׇ
    1.26
     as
    1.24
     tumbuhan
    1.23
     RISERV
    1.18
     newBuilder
    1.18
     with
    1.14
     when
    1.13
     without
    1.08
    Activations Density 0.054%

    No Known Activations