© 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. 22-GEMMASCOPE-RES-131K
    7. 26856
    Prev
    Next
    INDEX
    Explanations

    Listed buildings

    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_22/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
     プレス
    -0.97
     сним
    -0.91
    ,
    -0.85
    },
    -0.82
     stessi
    -0.79
     jūs
    -0.79
     {
    -0.78
     bencana
    -0.77
    ',['
    -0.77
     classiques
    -0.76
    POSITIVE LOGITS
     représentation
    1.02
    gencias
    0.94
    含义
    0.93
    arons
    0.92
    线性
    0.91
    ESTIC
    0.90
    czny
    0.90
    PREFACE
    0.90
     Sweatshirt
    0.89
    丐
    0.88
    Activations Density 0.007%

    No Known Activations