© 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. 34-GEMMASCOPE-RES-131K
    7. 92635
    Prev
    Next
    INDEX
    Explanations

    volume estimation or management

    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_34/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
    
    -1.18
     frumos
    -1.11
     vestito
    -1.07
    혔
    -1.05
    selbe
    -1.03
     pegat
    -1.01
     rapida
    -1.01
    
    -1.00
     debole
    -0.99
    
    -0.99
    POSITIVE LOGITS
     of
    1.41
     работы
    1.27
    </strong>
    1.26
     Volume
    1.24
    Vol
    1.21
    volume
    1.20
     vol
    1.16
     Vol
    1.16
     Volumen
    1.11
    vol
    1.09
    Activations Density 0.019%

    No Known Activations