© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90680
    Prev
    Next
    INDEX
    Explanations

    introduces additional 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
     with
    -1.96
    ),
    -1.77
     both
    -1.77
     
    -1.66
     It
    -1.66
     is
    -1.64
    </strong>
    -1.62
     has
    -1.59
     also
    -1.59
    ).
    -1.58
    POSITIVE LOGITS
    
    1.88
    
    1.87
     aussit
    1.86
    鮡
    1.73
    ኧ
    1.73
    瘆
    1.68
     chilen
    1.67
     menik
    1.66
    ㆆ
    1.66
     selam
    1.65
    Activations Density 0.005%

    No Known Activations