© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44964
    Prev
    Next
    INDEX
    Explanations

    enterprise systems and software

    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
    Accion
    -1.32
    komme
    -1.30
    Carex
    -1.23
     technische
    -1.21
     zape
    -1.16
    gün
    -1.16
    Bunny
    -1.14
    困难
    -1.14
    Réponse
    -1.13
    Etape
    -1.13
    POSITIVE LOGITS
     is
    1.39
    1.30
    </i>
    1.27
    I
    1.19
                      
    1.16
     bezpośrednio
    1.16
     />
    1.16
       
    1.15
     lepiej
    1.15
    を
    1.14
    Activations Density 0.078%

    No Known Activations