© 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. 128781
    Prev
    Next
    INDEX
    Explanations

    sorting code blocks

    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
    槟
    -1.37
     作り方
    -1.25
    釧
    -1.24
    Также
    -1.22
     همچنین
    -1.20
     nyeri
    -1.19
     豬
    -1.19
    Книга
    -1.14
     muze
    -1.12
     даже
    -1.10
    POSITIVE LOGITS
    AxisAlignment
    1.31
     például
    1.29
    (){
    1.29
     gevol
    1.27
    +'</
    1.26
    的時候
    1.22
    metheus
    1.22
    </b>
    1.20
     \%$
    1.18
     wtedy
    1.18
    Activations Density 0.001%

    No Known Activations