© 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. 10-GEMMASCOPE-RES-131K
    4. 112642
    Prev
    Next
    INDEX
    Explanations

    Trojan horse

    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
    苼
    -2.83
     unſ
    -2.81
     menacing
    -2.53
    </strong>
    -2.53
     ſever
    -2.48
    ݮ
    -2.42
     ſch
    -2.39
     dezelve
    -2.38
    摃
    -2.34
     ominous
    -2.31
    POSITIVE LOGITS
    an
    3.28
    ;
    
    3.17
    }$
    3.16
    </
    2.67
    );
    2.67
    ');
    
    2.66
    }>
    2.44
    },
    2.44
    ad
    2.42
    id
    2.41
    Activations Density 0.002%

    No Known Activations