© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3307
    Prev
    Next
    INDEX
    Explanations

    emoticons and )

    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
    */
    -0.91
    »,
    -0.86
    */;
    -0.85
    ."""
    -0.79
     problemas
    -0.77
    €¢
    -0.75
    };*/
    -0.75
    */
    -0.75
     Gait
    -0.74
    .*/
    -0.74
    POSITIVE LOGITS
     )
    2.08
     )
    1.70
     ).
    1.70
     );
    1.66
     ),
    1.51
     );
    1.45
     ):
    1.21
     }
    1.20
     ){
    1.19
     ))
    1.18
    Activations Density 0.004%

    No Known Activations