© 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. 75084
    Prev
    Next
    INDEX
    Explanations

    research findings and sources

    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
     and
    -1.28
     ......
    -1.15
     ....
    -1.11
     otros
    -1.09
    :[],
    -1.07
    erschein
    -1.06
    其中
    -1.05
     .....
    -1.05
    ândia
    -1.05
     سایر
    -1.05
    POSITIVE LOGITS
    為に
    1.72
     precedenti
    1.45
     zatrzy
    1.44
     knows
    1.38
     felé
    1.34
     inaczej
    1.31
     ocze
    1.28
     ervaring
    1.27
    際には
    1.26
     śnie
    1.24
    Activations Density 0.057%

    No Known Activations