© 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. 90110
    Prev
    Next
    INDEX
    Explanations

    zero physical parameters

    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
    lenie
    -0.72
    portable
    -0.71
     signifie
    -0.71
     tuyau
    -0.67
    deos
    -0.67
    imei
    -0.67
    ametri
    -0.66
     HONEY
    -0.66
    bread
    -0.66
     négy
    -0.65
    POSITIVE LOGITS
     timp
    0.67
     واس
    0.66
     Leah
    0.66
    arp
    0.65
     Kirche
    0.64
    監視
    0.63
    的说
    0.63
     examinar
    0.62
    sibilidade
    0.62
     rejected
    0.62
    Activations Density 0.047%

    No Known Activations