© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41802
    Prev
    Next
    INDEX
    Explanations

    i'm having

    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_10/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
     have
    -2.27
    .......
    -2.22
     .....
    -2.08
     specially
    -2.08
     For
    -2.06
    ....
    -1.98
     undoubtedly
    -1.98
    l
    -1.97
    .....
    -1.97
     began
    -1.96
    POSITIVE LOGITS
    𓁹
    2.33
    🫃
    2.31
    ⎔
    2.22
    ឵
    2.16
     miniaturka
    2.09
    
    2.06
     nieuwe
    2.03
     ſol
    2.02
    粜
    2.02
     différents
    1.95
    Activations Density 0.017%

    No Known Activations