© 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. 10-GEMMASCOPE-RES-131K
    4. 60531
    Prev
    Next
    INDEX
    Explanations

    ming, mixing, meld

    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
    end
    -2.44
    si
    -2.36
     same
    -2.30
     вызывает
    -2.28
    </h1>
    -2.25
    );
    
    -2.23
    }$
    -2.19
    };
    -2.17
    ਲ਼
    -2.16
    }\
    -2.06
    POSITIVE LOGITS
    
    2.14
     telep
    2.06
    giarism
    2.06
     バッジ
    2.03
     selben
    2.02
    賔
    1.99
    ????????
    1.98
    夘
    1.95
    辂
    1.95
     quot
    1.95
    Activations Density 0.003%

    No Known Activations