© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93197
    Prev
    Next
    INDEX
    Explanations

    dates and publications

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

    This neuron appears to be inactive (“dead”) and does not reliably respond to any textual 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_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
     nyeri
    -1.07
    样的
    -1.05
     menek
    -1.03
    所说
    -1.03
    がある
    -1.01
     infeksi
    -1.00
     addition
    -0.99
     this
    -0.99
     bañera
    -0.98
     öns
    -0.97
    POSITIVE LOGITS
    ••
    1.80
    
    1.47
    .•
    1.41
    眥
    1.35
    Of
    1.32
    耵
    1.32
     mußten
    1.27
    un
    1.19
    都不是
    1.19
    訁
    1.18
    Activations Density 0.009%

    No Known Activations