© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77369
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or list separators

    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
    Karakteristik
    -1.14
     only
    -1.13
     Bezir
    -1.11
    nachweise
    -1.04
     pemeriksaan
    -1.03
    Sebelum
    -1.03
     restos
    -1.02
    Tentang
    -1.01
     kemeja
    -1.01
    jacency
    -1.01
    POSITIVE LOGITS
    ;
    
    1.23
    );
    1.09
    );
    
    1.08
    )
    1.06
    .
    1.05
    ];
    1.01
    ,
    0.97
    });
    0.95
    0
    0.94
    ;
    0.92
    Activations Density 0.031%

    No Known Activations