© 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. 108001
    Prev
    Next
    INDEX
    Explanations

    Suboptimal, Gliwice, Q:

    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
    巩
    -0.80
    ጃ
    -0.72
    Duh
    -0.72
     Ces
    -0.71
     nabo
    -0.70
     Naidu
    -0.69
    Föld
    -0.68
     Gerber
    -0.68
     Вен
    -0.68
     窗
    -0.67
    POSITIVE LOGITS
    jsonwebtoken
    0.85
    fillStyle
    0.85
     Rother
    0.83
    üste
    0.82
     وصلة
    0.81
    αρ
    0.81
    phite
    0.80
    tainty
    0.78
    unte
    0.78
     routine
    0.78
    Activations Density 0.001%

    No Known Activations