© 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. 55631
    Prev
    Next
    INDEX
    Explanations

    monitoring and describing objects

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

    The neuron picks out specialized technical or domain-specific terminology in academic or scientific writing.

    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
    ➩
    -1.12
     calculations
    -1.12
    aneity
    -1.11
    Calculations
    -1.11
     будут
    -1.10
    lapping
    -1.08
    𝗼
    -1.08
    ü
    -1.05
     և
    -1.03
    :"#
    -1.03
    POSITIVE LOGITS
    ユーザ
    1.17
    maktadır
    1.03
     некото
    1.02
    Hence
    1.01
    FlatButton
    0.96
    TODO
    0.96
    דור
    0.96
    pée
    0.95
    如图
    0.95
     erzeugt
    0.95
    Activations Density 0.806%

    No Known Activations