© 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. 22-GEMMASCOPE-RES-131K
    4. 98312
    Prev
    Next
    INDEX
    Explanations

    concept followed by a specific noun

    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_22/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
     thoſe
    -1.37
     和
    -1.25
     imprimer
    -1.20
     obé
    -1.16
    utique
    -1.16
     craindre
    -1.16
     continuant
    -1.13
    cleros
    -1.10
    тивен
    -1.09
     hés
    -1.08
    POSITIVE LOGITS
     Когда
    1.11
     Kebijakan
    1.09
    <bos>
    1.09
     Lengkap
    1.04
    ることができます
    1.04
     ketentuan
    1.01
     assailed
    1.01
    웠
    1.00
     모든
    0.99
    莅
    0.97
    Activations Density 0.320%

    No Known Activations