© 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. 102440
    Prev
    Next
    INDEX
    Explanations

    code comments and string literals

    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
    ?
    -1.38
    !
    -1.26
    ...
    -1.06
     問題
    -1.05
    。
    -1.05
    ↵
    -1.04
     (
    -1.02
    ⁛
    -0.99
    …).
    -0.98
    animaux
    -0.98
    POSITIVE LOGITS
     */
    3.05
    */
    2.77
     */
    2.38
    */
    2.13
    </h2>
    2.06
    </td>
    1.96
    """
    1.90
     />
    1.89
    }
    1.80
    </h5>
    1.80
    Activations Density 0.059%

    No Known Activations