© 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. 34-GEMMASCOPE-RES-131K
    7. 50270
    Prev
    Next
    INDEX
    Explanations

    placement around physical 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_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
    manız
    -1.05
     THAT
    -1.04
     []:
    -1.01
    Δείτε
    -1.00
    }[
    -0.98
     konflikt
    -0.98
    önster
    -0.96
    ütten
    -0.95
     kollek
    -0.94
     geene
    -0.94
    POSITIVE LOGITS
     holder
    1.16
     housing
    1.08
     mounted
    1.05
     holders
    1.02
     mounting
    1.01
     Swag
    0.98
     bequem
    0.93
    도록
    0.93
    movable
    0.93
     céramique
    0.89
    Activations Density 0.125%

    No Known Activations