© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123943
    Prev
    Next
    INDEX
    Explanations

    personal information

    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
     are
    -1.70
    ciated
    -1.44
    );
    -1.41
     imperfect
    -1.41
     weren
    -1.41
    }:
    -1.39
     for
    -1.38
    ],
    -1.38
    ):
    
    -1.38
     );
    -1.34
    POSITIVE LOGITS
     навіть
    2.16
    焢
    1.81
    ஂ
    1.71
     別注
    1.67
    Cuando
    1.67
     даже
    1.66
    ハロウィン
    1.59
     حتی
    1.59
     Infór
    1.54
    
    1.52
    Activations Density 0.010%

    No Known Activations