© 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. 10-GEMMASCOPE-RES-131K
    7. 1792
    Prev
    Next
    INDEX
    Explanations

    implicit or implied concepts

    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
     })
    -1.24
    </i>
    -1.22
    台風
    -1.10
    
    -1.09
    dijo
    -1.09
     aldri
    -1.09
    ródła
    -1.09
     ruso
    -1.09
    薅
    -1.09
     haine
    -1.08
    POSITIVE LOGITS
    *
    1.38
     Ведь
    1.32
    Además
    1.20
     part
    1.19
    uk
    1.18
     идеально
    1.16
     автоматически
    1.16
    inerario
    1.16
     my
    1.14
    Finally
    1.14
    Activations Density 0.078%

    No Known Activations