© 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. 105663
    Prev
    Next
    INDEX
    Explanations

    ads, facebook, and sdk components

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

    class names and API identifiers in mobile development code, particularly for iOS and Android SDKs.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on names and keywords of advertising SDKs or ad‐related classes (e.g. “Ad,” “Ads,” “OfferWall,” “Flurry,” “IronSrc,” “Facebook,” etc.).

    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
     diputados
    -1.30
    ⮑
    -1.27
     we
    -1.27
    
    -1.23
    と同じ
    -1.23
     pouvons
    -1.20
    EEEEEEEE
    -1.20
     possono
    -1.19
     Algunos
    -1.17
     unbelievably
    -1.17
    POSITIVE LOGITS
     even
    1.74
    Even
    1.55
    After
    1.54
     first
    1.40
     while
    1.39
     after
    1.35
     additional
    1.34
    Following
    1.33
    mml
    1.32
    Having
    1.30
    Activations Density 0.058%

    No Known Activations