© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40154
    Prev
    Next
    INDEX
    Explanations

    OS X

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

    The neuron fires on occurrences of the standalone “OS” token (e.g. in “OS X” or similar operating‐system references).

    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
     the
    -2.84
    囯
    -2.58
    ሷ
    -2.45
    淠
    -2.33
    慥
    -2.25
    魮
    -2.23
    holding
    -2.23
     compiti
    -2.20
    雠
    -2.20
    此事
    -2.16
    POSITIVE LOGITS
    ↵↵
    2.67
    𖣘
    2.45
    ㌧
    2.38
     burbujas
    2.28
    ся
    2.19
     corrientes
    2.19
    ve
    2.16
     eminent
    2.13
     schicken
    2.13
     addition
    2.11
    Activations Density 0.009%

    No Known Activations