© 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. 61412
    Prev
    Next
    INDEX
    Explanations

    HDD, SSD, XRD

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

    The neuron spikes on three-letter uppercase acronyms (e.g. HDD, SSD, XRD).

    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
    Ⲉ
    -2.81
    琑
    -2.72
    嫆
    -2.63
    
    -2.44
    鸲
    -2.44
    銩
    -2.42
    ですので
    -2.33
    ’?
    -2.28
    setzt
    -2.28
    棪
    -2.27
    POSITIVE LOGITS
    C
    2.67
    \
    2.59
     —
    2.59
    H
    2.52
    F
    2.48
    一个月
    2.30
    P
    2.17
    晴れ
    2.16
     ,
    2.14
     мы
    2.13
    Activations Density 0.001%

    No Known Activations