© 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. 96
    Prev
    Next
    INDEX
    Explanations

    numbers and metrics

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

    The neuron activates on multi‐digit numeric tokens (i.e. numbers composed of several digits).

    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
    特長
    -2.13
    がありますが
    -2.11
    haviours
    -1.93
    
    -1.90
    は
    -1.88
    も
    -1.87
    Zubereitung
    -1.84
    琑
    -1.84
    を
    -1.84
     作り方
    -1.84
    POSITIVE LOGITS
    為に
    2.38
     and
    2.38
    0
    2.09
    に入れる
    1.89
    了不少
    1.89
     verschillende
    1.88
    ようです
    1.87
    9
    1.85
    7
    1.84
     to
    1.84
    Activations Density 0.126%

    No Known Activations