© 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. 117239
    Prev
    Next
    INDEX
    Explanations

    technical attributes and data

    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
     Friday
    -0.82
     Saturday
    -0.81
     Random
    -0.80
     YA
    -0.79
    ただ
    -0.77
    Random
    -0.74
     struct
    -0.72
    Capabilities
    -0.72
     Generic
    -0.72
     Hand
    -0.72
    POSITIVE LOGITS
     lievito
    0.84
    hadoop
    0.82
    xhr
    0.82
    solr
    0.81
    Sinopsis
    0.81
    Donor
    0.80
     ApiResponse
    0.79
     trattano
    0.79
     ajax
    0.78
    licitud
    0.78
    Activations Density 0.016%

    No Known Activations