© 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. 59262
    Prev
    Next
    INDEX
    Explanations

    bracketed citations and notations

    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
    靫
    -1.67
    芣
    -1.52
     forState
    -1.47
    
    -1.47
    ープン
    -1.42
     seksi
    -1.41
     nime
    -1.41
     akti
    -1.41
     vokal
    -1.32
     Dezember
    -1.30
    POSITIVE LOGITS
    .
    1.81
     if
    1.43
     einzelne
    1.37
     other
    1.33
    訁
    1.31
    这一点
    1.30
     podrán
    1.27
    見ても
    1.27
     farther
    1.27
     innych
    1.27
    Activations Density 0.035%

    No Known Activations