© 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. 39351
    Prev
    Next
    INDEX
    Explanations

    Chronicles, hadoop, Hessian, transversal

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

    The neuron flags tokens containing non‐ASCII letters—especially Latin characters with diacritics (like Romanian “ț”, “ș”, 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_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
    it
    -3.38
    am
    -3.00
    釭
    -2.86
    j
    -2.84
    enablog
    -2.81
    ০
    -2.80
    is
    -2.73
     If
    -2.69
    。」
    -2.61
    的一个
    -2.55
    POSITIVE LOGITS
    ↵
    3.19
    猹
    3.14
    艫
    3.11
    愎
    3.06
    ༀ
    2.86
    辚
    2.86
    憷
    2.50
    ⤞
    2.50
    要不是
    2.47
     ولكن
    2.42
    Activations Density 0.001%

    No Known Activations