© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35344
    Prev
    Next
    INDEX
    Explanations

    file paths

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

    The neuron is specialized to pick out standalone numeric tokens (e.g. version numbers or numbered directory names) in file paths and code listings.

    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
     its
    -1.49
     but
    -1.35
     you
    -1.17
     that
    -1.16
    はその
    -1.08
    卻
    -1.05
    bidities
    -1.03
    parseLong
    -1.02
    あげて
    -1.01
     ساعد
    -1.01
    POSITIVE LOGITS
    Preço
    1.13
    Postup
    1.07
    ᝢ
    1.06
     bambina
    1.05
     sposa
    1.02
    توضیحات
    1.02
     hickory
    1.00
    Doctoral
    1.00
    illa
    0.99
    Muito
    0.98
    Activations Density 0.005%

    No Known Activations