© 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. 68640
    Prev
    Next
    INDEX
    Explanations

    code snippets and data structures

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

    The neuron fires on sequences of digits, i.e. numeric tokens.

    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
     while
    -1.21
    ˂
    -1.13
     that
    -1.09
    addAll
    -1.06
    リット
    -1.02
    ,:),
    -1.01
    jmuje
    -0.99
     when
    -0.99
     seguras
    -0.99
    GeV
    -0.98
    POSITIVE LOGITS
     fatig
    0.96
     condol
    0.95
     pestil
    0.94
     momentous
    0.93
     éstos
    0.93
     './../
    0.91
    0
    0.90
     prestazioni
    0.90
     infernal
    0.89
     flamboyant
    0.88
    Activations Density 0.009%

    No Known Activations