© 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. 10-GEMMASCOPE-RES-131K
    7. 127607
    Prev
    Next
    INDEX
    Explanations

    Spanish auxiliary verbs + past participles

    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_10/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
    
    -2.53
     июня
    -2.31
    谞
    -2.22
    ،
    -2.17
    ización
    -2.16
    垟
    -2.13
    𓋼
    -2.13
    珎
    -2.11
     when
    -2.09
     thier
    -2.06
    POSITIVE LOGITS
     been
    2.86
    }];
    2.36
    </b>
    2.25
     $\$
    2.11
     communiquez
    2.05
    ]})
    1.93
    };*/
    1.91
     pasará
    1.85
     Use
    1.85
     \
    1.82
    Activations Density 0.002%

    No Known Activations