© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34786
    Prev
    Next
    INDEX
    Explanations

    Honda resurrects, Be Inspired

    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
     also
    -1.04
    ];
    -1.03
     '',
    -0.98
    進む
    -0.97
     still
    -0.95
     damp
    -0.93
     "",
    -0.90
    してみると
    -0.89
    也将
    -0.88
     Includes
    -0.87
    POSITIVE LOGITS
     ''}
    1.04
    `}
    1.00
    []}
    0.96
     ""}
    0.96
     スタンド
    0.93
    }
    0.91
    🐲
    0.91
    ковая
    0.89
     Concluding
    0.89
    。)
    0.87
    Activations Density 0.008%

    No Known Activations