© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60765
    Prev
    Next
    INDEX
    Explanations

    weapons and explosives

    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
     "";
    -1.25
    …」
    -1.18
     other
    -1.16
     berge
    -1.15
    Продол
    -1.15
    !」
    -1.14
    🌑
    -1.11
     canina
    -1.10
    isActive
    -1.07
     ;
    -1.06
    POSITIVE LOGITS
              
    1.23
    ஂ
    1.18
    </em>
    1.16
    Ᏹ
    1.15
     dostępne
    1.15
    phors
    1.13
     והוא
    1.12
                                  
    1.10
    龃
    1.07
    rassing
    1.05
    Activations Density 0.036%

    No Known Activations