© 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. 10258
    Prev
    Next
    INDEX
    Explanations

    objects in code or data structures

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

    the word "objects" in code and structured data files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron remains inactive (all-zero activations) and thus does not detect any specific pattern.

    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
    </h1>
    -2.84
    臜
    -2.58
    of
    -2.56
    沵
    -2.50
    鲥
    -2.33
    Saya
    -2.30
    蛲
    -2.28
    蒌
    -2.28
    en
    -2.25
     mehrere
    -2.23
    POSITIVE LOGITS
    </em>
    2.67
     If
    2.66
    guigu
    2.53
     cotidiano
    2.47
     localidades
    2.44
     sagrado
    2.41
     Also
    2.39
    𐄙
    2.39
     referido
    2.33
     ก็
    2.31
    Activations Density 0.011%

    No Known Activations