© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11402
    Prev
    Next
    INDEX
    Explanations

    proofreading team at http

    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
    ða
    -1.16
    ție
    -1.16
     AssemblyVersion
    -1.10
    醅
    -1.03
     ago
    -1.02
    います
    -0.99
     प्रतिशत
    -0.99
     моей
    -0.98
    性の
    -0.98
    dientemente
    -0.98
    POSITIVE LOGITS
    .
    1.30
     distinguer
    1.30
    ’
    1.18
     contagio
    1.10
     Mittwoch
    1.09
    4
    1.06
    9
    1.02
     öff
    1.02
     можуть
    1.02
    ۰۱
    1.01
    Activations Density 0.001%

    No Known Activations