© 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. 22-GEMMASCOPE-RES-131K
    7. 104381
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

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

    notation for numerical values or codes in scientific and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric tokens—especially standalone numbers and decimal fractions.

    oai_token-act-pair · o4-miniTriggered 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
     reç
    -1.21
    ครื่อง
    -1.19
    çok
    -1.18
    -1.16
     bienven
    -1.16
     sportif
    -1.13
     soin
    -1.12
    providedIn
    -1.11
    ادگی
    -1.11
     fré
    -1.10
    POSITIVE LOGITS
     again
    1.48
    1.44
    '
    1.28
     чаще
    1.27
    )
    1.24
    0
    1.22
    "
    1.22
    —
    1.20
    <bos>
    1.18
     mettere
    1.17
    Activations Density 0.000%
    No Known Activations