© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68561
    Prev
    Next
    INDEX
    Explanations

    medical/surgical or provider relationships

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

    The forward slash character ('/') when used to connect related terms or concepts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to forward‐slash characters (the “/” punctuation) 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
    が
    -1.84
    があり
    -1.80
    があります
    -1.69
    などが
    -1.64
    は
    -1.60
     花朵
    -1.52
    などは
    -1.51
    を
    -1.50
     dosis
    -1.48
     fenomen
    -1.46
    POSITIVE LOGITS
    ところに
    1.91
    ようです
    1.71
    様な
    1.65
    必要がある
    1.55
    気がします
    1.52
    ものです
    1.51
    Here
    1.46
     There
    1.46
    This
    1.46
    Only
    1.40
    Activations Density 0.058%

    No Known Activations