© 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. 117010
    Prev
    Next
    INDEX
    Explanations

    code and programming documentation

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

    The neuron predominantly responds to forward‐slash characters ("/") used as separators (e.g. in time notations like “10/9c,” URLs, file paths, etc.).

    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
    FloatField
    -0.77
     сла
    -0.71
    hp
    -0.69
    ontal
    -0.68
     successful
    -0.67
    εια
    -0.67
    Seek
    -0.66
    릭
    -0.66
    选择了
    -0.66
    agian
    -0.66
    POSITIVE LOGITS
    structs
    0.69
    PLEX
    0.67
    Ingress
    0.67
    userInfo
    0.66
     Judging
    0.66
     substr
    0.66
     sternum
    0.66
    gtest
    0.65
    estan
    0.64
     Reinhardt
    0.64
    Activations Density 0.073%

    No Known Activations