© 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. 22-GEMMASCOPE-RES-131K
    7. 36363
    Prev
    Next
    INDEX
    Explanations

    parts of systems or categories

    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
     जैसे
    -0.92
    %)$
    -0.88
     tõ
    -0.85
     entsteht
    -0.83
    rasse
    -0.83
    rauch
    -0.82
     chaque
    -0.82
     Rekord
    -0.82
    AFFIRMED
    -0.81
    еры
    -0.80
    POSITIVE LOGITS
    יו
    1.06
    짬
    0.93
     collection
    0.90
     possibilities
    0.89
     BROTHERS
    0.87
     Latein
    0.87
     together
    0.85
     pool
    0.85
     мъ
    0.84
     pengar
    0.83
    Activations Density 0.095%

    No Known Activations