© 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. 34-GEMMASCOPE-RES-131K
    7. 47475
    Prev
    Next
    INDEX
    Explanations

    PHP opening tag

    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_34/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
     Wirken
    -1.06
    msgTypes
    -1.05
    '},
    -1.01
    imax
    -1.01
     eorum
    -1.00
    </h6>
    -0.98
    "},
    -0.97
     disegni
    -0.96
    に行ってきました
    -0.95
     Arzne
    -0.94
    POSITIVE LOGITS
    Zel
    0.98
     Spill
    0.90
    mathit
    0.90
    癞
    0.89
     liberté
    0.87
     IPv
    0.85
     Carpet
    0.85
     pessoas
    0.83
    看似
    0.83
     ARM
    0.82
    Activations Density 0.532%

    No Known Activations