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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2982
    Prev
    Next
    INDEX
    Explanations

    closing delimiters and quotes

    np_acts-logits-general · gemini-2.5-flash-lite

    incrementing counter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     */;
    0.54
    ';
    0.50
    }{}
    0.46
    ’;
    0.46
    ”;
    0.45
    』(
    0.44
    ];//
    0.44
    </blockquote>
    0.44
    ]";
    0.43
    /';
    0.43
    POSITIVE LOGITS
    "))
    2.03
    ."))
    2.03
     ""))
    2.00
    ()))
    1.97
    ))
    1.94
    '))
    1.94
    "));
    1.93
    ()));
    1.92
    ))
    1.86
    '));
    1.85
    Activations Density 0.029%

    No Known Activations