© 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. 111218
    Prev
    Next
    INDEX
    Explanations

    correctness and incorrectness

    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
    \\
    -1.84
    ’
    -1.81
    ]
    -1.62
    >
    -1.58
    </h3>
    -1.55
    まっている
    -1.43
    camiento
    -1.41
    -
    -1.41
     have
    -1.38
    \
    -1.38
    POSITIVE LOGITS
     anest
    1.61
    渽
    1.59
    気付
    1.59
     Ausrüstung
    1.57
    though
    1.53
    相変わらず
    1.47
     Să
    1.46
     sedia
    1.46
    ,  
    1.45
    躊
    1.45
    Activations Density 0.068%

    No Known Activations