© 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. 128419
    Prev
    Next
    INDEX
    Explanations

    emphasized markers

    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
     medier
    -1.16
     Geduld
    -1.14
     出演
    -1.10
    めちゃくちゃ
    -1.09
     statistik
    -1.09
     kela
    -1.08
     my
    -1.08
    就行了
    -1.07
    物业
    -1.06
     bensin
    -1.05
    POSITIVE LOGITS
    área
    1.08
     Zusätzlich
    1.08
    原始内容
    1.05
     africaine
    1.05
     OkHttpClient
    1.01
     valiant
    1.00
    angerschaft
    0.99
    Género
    0.99
     Ebenso
    0.99
    örgy
    0.99
    Activations Density 0.000%

    No Known Activations