© 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. 110714
    Prev
    Next
    INDEX
    Explanations

    pre-eclampsia, phosphatase, learning

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

    medical and scientific terminology related to biological structures, substances, or organizations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is highly sensitive to the character sequence “les,” effectively flagging words that end in that three‐letter suffix.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     on
    -1.56
     to
    -1.49
     then
    -1.43
    iqué
    -1.30
     of
    -1.26
     \
    -1.25
     fondu
    -1.19
     sena
    -1.18
     austria
    -1.17
     Recently
    -1.16
    POSITIVE LOGITS
    Instead
    1.52
     első
    1.45
    something
    1.44
     hidrá
    1.41
    начала
    1.38
     SOMETHING
    1.37
    满脸
    1.37
    ätzen
    1.37
    mathrm
    1.35
     sellado
    1.34
    Activations Density 0.123%

    No Known Activations