© 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. 22-GEMMASCOPE-RES-131K
    7. 25476
    Prev
    Next
    INDEX
    Explanations

    first initial early

    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_22/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
     последний
    -0.92
    Recent
    -0.92
     اخیر
    -0.91
    Recently
    -0.91
    Last
    -0.90
     recentemente
    -0.88
    最近
    -0.85
     wiederum
    -0.84
     poslední
    -0.84
     dernières
    -0.82
    POSITIVE LOGITS
     early
    3.03
     initial
    2.78
     initially
    2.50
     초기
    2.20
     earliest
    2.20
     inicial
    2.20
     first
    2.19
     Initially
    2.06
     before
    2.03
    แรก
    2.03
    Activations Density 0.138%

    No Known Activations