© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25593
    Prev
    Next
    INDEX
    Explanations

    multi-lingual content or programming keywords

    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
    Étape
    -0.93
     mercen
    -0.93
     &#
    -0.90
     brisa
    -0.89
     saiu
    -0.88
    Série
    -0.84
     essencial
    -0.82
    𝐖
    -0.82
     madeira
    -0.82
    openid
    -0.81
    POSITIVE LOGITS
     Avez
    0.92
     turquesa
    0.89
     niebieski
    0.86
     gröss
    0.86
    מבר
    0.85
    ğe
    0.84
     empfehlen
    0.83
     champs
    0.83
    ểu
    0.83
     hetzelfde
    0.82
    Activations Density 0.021%

    No Known Activations