© 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. 12784
    Prev
    Next
    INDEX
    Explanations

    Qatar

    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
    ৫
    -1.66
     серый
    -1.53
     bezpiecze
    -1.47
    一旁
    -1.44
     our
    -1.41
     informacje
    -1.37
     będ
    -1.36
    𓋼
    -1.31
    mathrm
    -1.30
     太郎
    -1.30
    POSITIVE LOGITS
    </em>
    1.63
     maravillosas
    1.48
     hermosas
    1.38
     énorme
    1.30
     offrent
    1.30
    Docente
    1.28
     appreciable
    1.27
     plongée
    1.24
     légumes
    1.23
     —
    1.23
    Activations Density 0.001%

    No Known Activations