© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15254
    Prev
    Next
    INDEX
    Explanations

    Nexus

    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
    祤
    -2.64
     rosse
    -2.61
    籴
    -2.58
    your
    -2.50
    ússia
    -2.48
    ︕
    -2.47
    饜
    -2.39
    遹
    -2.36
    瀦
    -2.36
    ";
    -2.36
    POSITIVE LOGITS
    ?"
    2.39
     "
    2.33
        
    2.27
    ar
    2.25
     ]
    2.11
    但他
    2.08
     
    2.06
    ’
    2.02
    ?'
    2.02
     insist
    1.95
    Activations Density 0.005%

    No Known Activations