© 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. 73399
    Prev
    Next
    INDEX
    Explanations

    mechanism in, viruses from, referred to

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

    copyright notices and license information in software and content files.

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

    The neuron fires strongly on tokens that are purely numeric (e.g. version numbers, counts, year‐like or digit‐only strings).

    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
    határoz
    -0.80
    Wymiary
    -0.75
    <h2>
    -0.73
     effectively
    -0.71
    مال
    -0.70
    輊
    -0.69
    ūra
    -0.69
     owners
    -0.68
    OPHER
    -0.68
     securely
    -0.68
    POSITIVE LOGITS
    ↵↵↵
    1.20
    textbackslash
    1.09
    ↵↵↵↵
    0.96
    \}
    0.87
    (")
    0.81
     المرت
    0.79
    /")
    0.77
    Abstra
    0.76
    鬢
    0.75
    鬓
    0.75
    Activations Density 0.000%

    No Known Activations