© 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. 63996
    Prev
    Next
    INDEX
    Explanations

    months and specific roles

    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
    Servicios
    -0.93
    ,«
    -0.84
    interface
    -0.82
     Tonic
    -0.80
     Gecko
    -0.79
    😐
    -0.79
    projek
    -0.78
     »>
    -0.78
    polski
    -0.77
     sona
    -0.76
    POSITIVE LOGITS
    ண்
    0.91
     Mic
    0.78
     Call
    0.77
    への
    0.76
    踩
    0.75
    rored
    0.74
     bilg
    0.73
     hatch
    0.73
     كما
    0.73
     Enter
    0.72
    Activations Density 0.008%

    No Known Activations