© 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. 10-GEMMASCOPE-RES-131K
    4. 23995
    Prev
    Next
    INDEX
    Explanations

    moz prefixes, units, callsigns, identifiers

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

    The neuron fires on short uppercase letter sequences (acronyms/codes), such as call-signs, strain IDs, vendor prefixes, or other all-caps abbreviations.

    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
     unparalleled
    -2.50
     increase
    -2.47
    隄
    -2.45
    tyfik
    -2.45
     incessant
    -2.44
     longstanding
    -2.39
     отредактировал
    -2.39
    甡
    -2.36
    ⤙
    -2.36
     unbelievable
    -2.34
    POSITIVE LOGITS
    1
    4.25
    8
    3.08
    c
    2.98
    2
    2.95
    3
    2.89
    9
    2.89
    "
    2.56
    OR
    2.53
    튿
    2.50
    ?"
    2.48
    Activations Density 0.008%

    No Known Activations