© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66340
    Prev
    Next
    INDEX
    Explanations

    names and varieties

    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
     calavera
    -1.55
     emblema
    -1.49
     Garanti
    -1.42
     presunto
    -1.40
     misterio
    -1.37
     Politica
    -1.36
     falda
    -1.34
     leopardo
    -1.34
    Ofer
    -1.32
     misericordia
    -1.30
    POSITIVE LOGITS
     Too
    1.27
    fordshire
    1.27
    лаго
    1.27
    sc
    1.22
    tocks
    1.19
    therners
    1.16
    du
    1.16
     quiso
    1.13
     ifølge
    1.12
     samtidig
    1.11
    Activations Density 0.008%

    No Known Activations