© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85773
    Prev
    Next
    INDEX
    Explanations

    called for

    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
    }
    -1.96
     scheinen
    -1.93
     greifen
    -1.92
     erila
    -1.86
     what
    -1.78
    ieteur
    -1.73
    ensdag
    -1.72
    几个
    -1.71
     esimer
    -1.70
     siinä
    -1.70
    POSITIVE LOGITS
    ouſ
    2.11
     oorsp
    2.02
    ⸨
    1.97
     is
    1.93
    涐
    1.90
    <<<<<<<<<<<<
    1.84
    戆
    1.79
     and
    1.78
    ܃
    1.77
    蚡
    1.77
    Activations Density 0.012%

    No Known Activations