© 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. 90892
    Prev
    Next
    INDEX
    Explanations

    code comments and citations

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

    The neuron fires on any token fragment containing the substring “asm.”

    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
     are
    -1.82
    кости
    -1.45
    thinkable
    -1.44
    すでに
    -1.42
    での
    -1.41
     Даже
    -1.41
    чни
    -1.38
    では
    -1.38
     使っ
    -1.38
     rene
    -1.38
    POSITIVE LOGITS
    ﹶ
    1.50
    Ꮸ
    1.49
    所说的
    1.47
     Fahrrad
    1.43
    },[])
    1.41
     October
    1.40
     slightly
    1.39
    {
    1.38
     less
    1.36
    ︒
    1.34
    Activations Density 0.000%

    No Known Activations