© 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. 50203
    Prev
    Next
    INDEX
    Explanations

    distance

    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
    lamation
    -0.78
    zept
    -0.77
    nels
    -0.77
    ˬ
    -0.76
    Swing
    -0.76
    ulador
    -0.75
    วัติ
    -0.75
    imgur
    -0.74
    Kaynakça
    -0.74
     Vimeo
    -0.72
    POSITIVE LOGITS
     distance
    7.59
    distance
    6.03
     distances
    6.00
     Distance
    5.53
    Distance
    5.50
    距離
    4.72
     distancia
    4.72
    距离
    4.53
    DISTANCE
    4.50
     DISTANCE
    4.44
    Activations Density 0.164%

    No Known Activations