© 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. 64945
    Prev
    Next
    INDEX
    Explanations

    recent past events

    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
    そのため
    -1.45
     they
    -1.30
     instead
    -1.26
     each
    -1.21
    젬
    -1.16
     today
    -1.15
     premat
    -1.15
    そして
    -1.13
    与此同时
    -1.13
     jurk
    -1.10
    POSITIVE LOGITS
    おわりに
    1.46
    ึกษา
    1.23
     married
    1.14
    レーター
    1.09
    lenovo
    1.09
    鑾
    1.07
     степени
    1.06
    だよね
    1.05
    кономи
    1.04
     matematika
    1.04
    Activations Density 0.084%

    No Known Activations