© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110792
    Prev
    Next
    INDEX
    Explanations

    data adapter fill

    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
     actionBar
    -0.79
    хова
    -0.78
     сорта
    -0.77
     scena
    -0.76
    creator
    -0.75
     家具
    -0.75
     Pudding
    -0.75
    ?".
    -0.75
     Hes
    -0.74
    atic
    -0.74
    POSITIVE LOGITS
    ystis
    0.92
     queries
    0.90
    TableAdapter
    0.85
    pecified
    0.78
    ulia
    0.78
    ubmit
    0.77
     adap
    0.77
    的自
    0.77
     inserted
    0.77
    ismic
    0.76
    Activations Density 0.001%

    No Known Activations