© 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. 14034
    Prev
    Next
    INDEX
    Explanations

    database collection paths

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

    The neuron fires on code-style identifiers and field/key names (e.g. API method calls, config/document field names) rather than ordinary words.

    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
     waarom
    -1.16
    不是
    -0.99
    athered
    -0.98
    不要
    -0.98
    不能
    -0.96
     både
    -0.94
     autres
    -0.94
    opie
    -0.94
     NOT
    -0.93
     avec
    -0.92
    POSITIVE LOGITS
    Новая
    1.08
    Вопрос
    1.08
    tać
    1.07
     cobrar
    1.07
    Phân
    1.05
    Detalhes
    1.02
    Siapa
    1.01
    ízo
    1.00
    ământ
    0.97
    Dzień
    0.97
    Activations Density 0.002%

    No Known Activations