© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129451
    Prev
    Next
    INDEX
    Explanations

    proof of concept or principle

    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_10/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
    ！」
    -1.29
     различни
    -1.23
    iczne
    -1.17
     hlavy
    -1.16
    opcao
    -1.16
    或者
    -1.16
     всѣ
    -1.16
    主要
    -1.13
     неё
    -1.13
    ⌫
    -1.12
    POSITIVE LOGITS
     time
    1.43
     demonstrated
    1.40
     price
    1.35
     intenção
    1.28
    ⌉
    1.23
     anybody
    1.22
     دب
    1.21
     Τ
    1.20
     cost
    1.19
     success
    1.19
    Activations Density 0.110%

    No Known Activations