© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98650
    Prev
    Next
    INDEX
    Explanations

    software licenses and code

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

    The neuron is triggered by numeric digit sequences (e.g. years or multi‐digit numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    GPU
    -0.92
    boucles
    -0.85
     déplacements
    -0.83
    の新
    -0.82
     retours
    -0.81
    yep
    -0.81
    stdafx
    -0.79
     débats
    -0.79
    ἓ
    -0.78
     dvd
    -0.77
    POSITIVE LOGITS
    TypeDef
    0.88
     OSError
    0.82
     Nutt
    0.81
    pherals
    0.80
     board
    0.80
    flashdata
    0.80
    androidx
    0.79
     SPDX
    0.79
    bę
    0.78
     MCU
    0.78
    Activations Density 0.053%

    No Known Activations