© 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. 22-GEMMASCOPE-RES-131K
    4. 98436
    Prev
    Next
    INDEX
    Explanations

    sp followed by specific suffixes

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

    The neuron strongly activates on the subtoken “sp” (in any casing), as it appears in things like “SP1,” “sp_executesql,” “addSponsorship,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the token "sp" when it appears as an abbreviation for "sponsor", "service pack", "stored procedure", or in technical/code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     imprimi
    -2.78
     
    -2.66
     obrigado
    -2.44
    </b>
    -2.39
    木坂
    -2.33
     envia
    -2.28
     encontre
    -2.25
     encontro
    -2.22
    中有
    -2.20
     acontece
    -2.17
    POSITIVE LOGITS
    i
    2.64
    鬭
    2.63
    ed
    2.52
     Для
    2.47
    <bos>
    2.44
    u
    2.42
     کردند
    2.31
    ஂ
    2.23
    </h3>
    2.22
    Зно
    2.22
    Activations Density 0.075%

    No Known Activations