© 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. 70423
    Prev
    Next
    INDEX
    Explanations

    cyclical and cyclization

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

    words related to chemical cyclization processes, particularly terms containing "cycl" like "cyclical" and "cyclization".

    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
    __":
    -2.28
     Mostly
    -2.11
    OLVED
    -2.05
    msford
    -2.05
     “…
    -2.03
     Даже
    -2.02
     verbess
    -2.02
    当時は
    -2.00
    ли
    -1.99
    larda
    -1.98
    POSITIVE LOGITS
    "
    2.56
     avec
    2.44
    }$
    2.27
    a
    2.20
    u
    2.02
     They
    1.99
    :
    1.98
    '
    1.95
     Their
    1.95
     et
    1.90
    Activations Density 0.003%

    No Known Activations