© 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. 10-GEMMASCOPE-RES-131K
    7. 42795
    Prev
    Next
    INDEX
    Explanations

    d or D

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

    The neuron activates on numeric tokens (digits or numbers, often embedded in code/config entries).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     your
    -1.19
    ervous
    -1.18
    idance
    -1.17
    大幅
    -1.17
     где
    -1.16
     spiaggia
    -1.13
    efty
    -1.13
     macchina
    -1.12
     }
    -1.11
     Organisator
    -1.10
    POSITIVE LOGITS
     they
    1.66
     они
    1.37
     hefyd
    1.27
     mereka
    1.24
    ífonos
    1.21
    犷
    1.13
     principes
    1.13
     for
    1.12
    ğlu
    1.09
    ⸰
    1.09
    Activations Density 0.200%

    No Known Activations