© 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. 22-GEMMASCOPE-RES-131K
    4. 67337
    Prev
    Next
    INDEX
    Explanations

    questions, lists, or specific formatting

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

    The neuron is primarily activated by numeric tokens—especially decimal or measurement values.

    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
     cristianos
    -1.21
    思います
    -1.21
    着的
    -1.14
    ∓
    -1.14
    Ѕ
    -1.14
    檗
    -1.13
     única
    -1.12
    urazione
    -1.09
    ('/:
    -1.06
    durable
    -1.05
    POSITIVE LOGITS
     and
    1.45
    .
    1.38
     rendono
    1.27
    8
    1.11
    ;
    
    1.09
    OUR
    1.09
    2
    1.05
    院校
    1.01
    7
    1.00
     vanno
    0.99
    Activations Density 0.000%

    No Known Activations