© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2360
    Prev
    Next
    INDEX
    Explanations

    symbols and their translations

    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
    ),
    -1.48
    érienne
    -1.38
    ],
    -1.11
     Therefore
    -1.07
    },
    -1.06
    所以在
    -1.06
    —
    -1.06
     umgekehrt
    -1.04
     mehrm
    -1.02
     —
    -1.00
    POSITIVE LOGITS
     besonders
    1.44
     também
    1.42
     también
    1.38
     również
    1.34
     także
    1.33
     myös
    1.27
     également
    1.26
     также
    1.26
     ainda
    1.26
     auch
    1.20
    Activations Density 0.306%

    No Known Activations