© 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. 118786
    Prev
    Next
    INDEX
    Explanations

    words starting with intra

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

    The neuron consistently activates on words beginning with the prefix “intra-” (e.g. intranet, intrathoracic, intrafasicular, intraneural, intramuscular).

    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
    衚
    -2.64
    汌
    -2.50
    geox
    -2.23
    ܊
    -2.22
    葑
    -2.19
     Púb
    -2.17
     Públicas
    -2.16
     gethan
    -2.16
    俅
    -2.14
    荩
    -2.14
    POSITIVE LOGITS
    \
    2.41
     BOTH
    2.34
    на
    2.28
    s
    2.25
     beiden
    2.23
    ).
    2.02
    ".
    1.95
    霎
    1.92
    da
    1.91
    each
    1.88
    Activations Density 0.013%

    No Known Activations