© 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. 80681
    Prev
    Next
    INDEX
    Explanations

    as expected

    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
     porque
    -1.55
    ',
    -1.48
    ],
    -1.46
    ()',
    -1.46
    趼
    -1.43
    Anlage
    -1.41
    '],
    -1.40
    '),
    -1.38
    
    -1.37
    ᾥ
    -1.37
    POSITIVE LOGITS
    The
    1.37
     trouverez
    1.35
    Already
    1.30
    ,
    1.28
     fragte
    1.27
     with
    1.27
    他の
    1.24
     وقع
    1.20
    They
    1.20
     overall
    1.14
    Activations Density 0.017%

    No Known Activations