© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106390
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    playSound
    -0.90
    award
    -0.88
    notifyListeners
    -0.85
    vidades
    -0.84
    мар
    -0.82
     Kategor
    -0.82
    mentary
    -0.82
     USB
    -0.81
     Số
    -0.81
    removeFrom
    -0.80
    POSITIVE LOGITS
     necessários
    0.98
     empezar
    0.98
     medewerkers
    0.96
     comenzar
    0.93
     garantizar
    0.93
     ejercer
    0.93
     enabling
    0.92
     contratar
    0.92
     working
    0.91
     fijar
    0.91
    Activations Density 0.039%

    No Known Activations