© 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. 67298
    Prev
    Next
    INDEX
    Explanations

    what i want to do

    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
    ските
    -1.31
    鸸
    -1.30
    itern
    -1.29
     cauſe
    -1.28
     père
    -1.27
     itin
    -1.26
    
    -1.26
     hotelu
    -1.25
     csak
    -1.24
     paiement
    -1.24
    POSITIVE LOGITS
     is
    2.38
    is
    1.51
     time
    1.38
    A
    1.38
    ↵↵
    1.34
    After
    1.33
     may
    1.30
    H
    1.26
     happen
    1.26
    N
    1.25
    Activations Density 0.059%

    No Known Activations