© 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. 113814
    Prev
    Next
    INDEX
    Explanations

    architecture identifiers

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

    references to 64-bit computer architectures (like arm64, amd64, ppc64, i386/64).

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

    The neuron flags CPU architecture identifiers and their numeric-size tokens (e.g., “arm,” “64,” “6,” “4,” 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
     on
    -1.62
    ing
    -1.45
    ↵
    -1.43
     et
    -1.41
    mathrm
    -1.39
     because
    -1.34
     their
    -1.30
    之为
    -1.30
     allowing
    -1.29
    amos
    -1.25
    POSITIVE LOGITS
    渽
    1.47
     zajíma
    1.45
     všechny
    1.41
    尬
    1.39
     Reſ
    1.37
     发
    1.36
     veľmi
    1.36
    ходит
    1.36
    goes
    1.34
     obyvateľov
    1.34
    Activations Density 0.064%

    No Known Activations