© 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. 48770
    Prev
    Next
    INDEX
    Explanations

    Java collection instantiation

    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
     begge
    -0.96
     ...'
    -0.96
    "):
    
    -0.91
    minton
    -0.91
     even
    -0.91
     ...)
    -0.90
     però
    -0.88
    ")
    
    -0.85
    warded
    -0.84
    ÉD
    -0.84
    POSITIVE LOGITS
    ();
    2.03
    <>();
    1.56
    ();
    
    1.44
    ());
    1.30
    >();
    1.25
    ];
    1.15
     [];
    1.11
    };
    1.11
     {};
    1.09
    <>
    1.06
    Activations Density 0.001%

    No Known Activations