© 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. 28433
    Prev
    Next
    INDEX
    Explanations

    starts of different content types

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

    The neuron fires on multi‐digit numeric tokens (e.g. price or level figures).

    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
     стандарт
    -1.04
    개
    -1.01
     рисунок
    -0.99
    ▷
    -0.98
     tigre
    -0.96
    ⇨
    -0.95
    Choosing
    -0.95
    駸
    -0.95
     Процитовано
    -0.94
     настолько
    -0.94
    POSITIVE LOGITS
     and
    1.00
    Disliked
    0.98
     Heute
    0.96
    みたいに
    0.96
    してみた
    0.96
    Obfusc
    0.96
    7
    0.96
    Techno
    0.96
    3
    0.94
     today
    0.94
    Activations Density 0.003%

    No Known Activations