© 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. 22-GEMMASCOPE-RES-131K
    7. 35433
    Prev
    Next
    INDEX
    Explanations

    software versions and updates

    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
     katholischen
    -1.59
     kathol
    -1.39
     tradicional
    -1.34
     ДТП
    -1.23
    }}_
    -1.21
    ׇ
    -1.17
     traditional
    -1.16
    )|^{
    -1.15
     EdgeInsets
    -1.14
     گیاه
    -1.14
    POSITIVE LOGITS
     versions
    1.48
     latest
    1.45
     version
    1.42
    LATEST
    1.22
     currently
    1.22
     getNew
    1.22
     getAge
    1.16
     Pilihan
    1.13
     newest
    1.13
    ragon
    1.13
    Activations Density 0.193%

    No Known Activations