© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40878
    Prev
    Next
    INDEX
    Explanations

    Q/Echo

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

    The neuron strongly activates on the Ruby hash‐rocket operator “=>” whenever a hash key/value pair is being defined.

    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
     verbeter
    -1.56
    下意识
    -1.48
    ……………………
    -1.44
     ..............
    -1.43
     It
    -1.41
    oeuvre
    -1.40
     kurzem
    -1.40
    檮
    -1.39
     sodass
    -1.38
     意思
    -1.37
    POSITIVE LOGITS
     richiesto
    1.80
    ()]);
    1.72
     terzo
    1.72
    asional
    1.70
    ⟝
    1.63
     органы
    1.47
     scelto
    1.46
    ++];
    1.45
    之以
    1.45
    その
    1.43
    Activations Density 0.005%

    No Known Activations