© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63065
    Prev
    Next
    INDEX
    Explanations

    documents scheduled

    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
     holiness
    -0.94
     pož
    -0.85
    ssant
    -0.84
     patrons
    -0.82
     strait
    -0.81
    īga
    -0.80
    🧹
    -0.79
    koń
    -0.79
     înd
    -0.76
    eket
    -0.76
    POSITIVE LOGITS
     opie
    0.83
     также
    0.77
    各種
    0.75
     lo
    0.74
     również
    0.73
     triste
    0.73
     vyd
    0.70
    various
    0.70
     пред
    0.69
     también
    0.68
    Activations Density 0.003%

    No Known Activations