© 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. 26040
    Prev
    Next
    INDEX
    Explanations

    decoding codes

    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
     comics
    -0.75
     př
    -0.73
    亚洲
    -0.72
     episodes
    -0.71
     episode
    -0.69
     lace
    -0.68
     quarantine
    -0.68
    genza
    -0.68
    setNew
    -0.67
     mechanistic
    -0.67
    POSITIVE LOGITS
     decoding
    1.16
    decoder
    1.09
     Viter
    1.03
     decode
    1.02
    decode
    1.02
    Decode
    1.02
     decoder
    1.02
    Decoding
    1.00
     Codes
    0.98
    PSK
    0.95
    Activations Density 0.100%

    No Known Activations