© 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. 97909
    Prev
    Next
    INDEX
    Explanations

    mint and peppermint

    np_acts-logits-general · gemini-2.5-flash-lite

    Linux distribution names, particularly "Mint" with version numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    dighet
    -0.76
     lány
    -0.74
    ppler
    -0.74
     Heizung
    -0.70
     concerned
    -0.68
    
    -0.68
    tober
    -0.67
     &___
    -0.67
    職
    -0.67
     négy
    -0.66
    POSITIVE LOGITS
     Jule
    1.27
     jule
    1.25
     condition
    1.05
     moj
    0.98
     ITT
    0.96
     Moj
    0.93
     MINT
    0.91
    Mint
    0.86
     Chip
    0.83
    condition
    0.82
    Activations Density 0.020%

    No Known Activations