© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 62992
    Prev
    Next
    INDEX
    Explanations

    code comments and licenses

    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
    ⌉
    -0.84
    に変
    -0.72
    })}
    -0.71
    </h1>
    -0.70
    </strong>
    -0.69
     periodical
    -0.69
    idine
    -0.68
     conversation
    -0.68
    Soldier
    -0.68
     hadas
    -0.67
    POSITIVE LOGITS
     */
    2.53
    */
    2.30
     */
    
    2.23
    */
    
    1.73
    =*/
    1.38
     */;
    1.27
    ;*/
    1.27
    <h5>
    1.25
     */
    
    
    1.23
    )*/
    1.20
    Activations Density 0.239%

    No Known Activations