© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1471
    Prev
    Next
    INDEX
    Explanations

    NLP and neuro concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     私
    -0.84
     adiv
    -0.81
     imig
    -0.80
     puo
    -0.77
     Malmö
    -0.75
    wendung
    -0.75
     diskusi
    -0.75
     laim
    -0.75
     Alois
    -0.75
    Wire
    -0.74
    POSITIVE LOGITS
     NLP
    1.73
     Neuro
    1.32
    NLP
    1.30
     neuro
    1.26
    Neuro
    1.08
    nlp
    1.07
     linguistic
    1.06
    neuro
    1.02
     neu
    0.98
     Neurol
    0.94
    Activations Density 0.007%

    No Known Activations