© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79795
    Prev
    Next
    INDEX
    Explanations

    start of phrases

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

    The neuron is a detector for numeric tokens (i.e. standalone numbers) in the text.

    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
     it
    -1.41
    Моя
    -1.20
    Поэтому
    -1.13
     fön
    -1.11
    Приятного
    -1.10
    Einsatz
    -1.08
     étr
    -1.08
    Мои
    -1.06
    Смотрите
    -1.05
     kriminal
    -1.04
    POSITIVE LOGITS
     distinguishing
    1.01
    暧
    1.01
     into
    0.98
    vaila
    0.96
     manner
    0.96
    ic
    0.95
    ticing
    0.93
     his
    0.93
     '/':
    0.93
    ient
    0.93
    Activations Density 0.004%

    No Known Activations