© 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. 100896
    Prev
    Next
    INDEX
    Explanations

    dimorphic fungus

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

    The neuron detects forms of the word "dim" and related terms like "dimple", "dimorphic", and "dimer".

    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
     Debido
    -2.45
     Allí
    -2.42
     Algunas
    -2.39
     Había
    -2.33
     modernen
    -2.30
     individuellen
    -2.28
     Também
    -2.25
    頽
    -2.25
     手作り
    -2.25
     außerord
    -2.23
    POSITIVE LOGITS
    \
    3.92
     '
    2.52
    1
    2.42
     quattro
    2.31
     QtCore
    2.17
    fying
    2.16
     strerror
    2.16
     Для
    2.14
    鉏
    2.13
    </strong>
    2.09
    Activations Density 0.006%

    No Known Activations