© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21970
    Prev
    Next
    INDEX
    Explanations

    Angular, Vue, EmberJS, components

    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
     are
    -1.35
     peggio
    -1.16
     sapere
    -1.15
     radioButton
    -1.12
     prosegu
    -1.11
     alcuni
    -1.10
     devono
    -1.09
     joke
    -1.09
     affatto
    -1.09
     peccato
    -1.08
    POSITIVE LOGITS
     completos
    1.21
     argentinos
    1.20
    Trying
    1.20
    
    1.19
    马来西亚
    1.19
     Nosotros
    1.16
     conectados
    1.14
     bibliothèque
    1.13
    Tickets
    1.13
     vines
    1.12
    Activations Density 0.129%

    No Known Activations