© 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. 34-GEMMASCOPE-RES-131K
    7. 33437
    Prev
    Next
    INDEX
    Explanations

    Pages Q

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

    The neuron is primarily picking up numeric literal tokens in code (e.g. standalone numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     never
    -2.03
    Never
    -1.60
    never
    -1.53
     никогда
    -1.48
     Never
    -1.47
     nooit
    -1.36
     jamais
    -1.32
     nunca
    -1.28
     NEVER
    -1.25
     कभी
    -1.19
    POSITIVE LOGITS
     let
    1.38
    let
    1.16
     apalagi
    0.96
    時から
    0.83
     Behör
    0.83
    Let
    0.81
     deixou
    0.80
    בּ
    0.78
    won
    0.77
     Let
    0.76
    Activations Density 0.003%

    No Known Activations