© 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. 93207
    Prev
    Next
    INDEX
    Explanations

    open or closed status

    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
    []=$
    -0.87
     سيارة
    -0.84
     stalled
    -0.84
     hospitals
    -0.83
     strikingly
    -0.82
     بیمارستان
    -0.82
     reemplazar
    -0.81
     платье
    -0.80
     desaparecido
    -0.80
    hôpital
    -0.79
    POSITIVE LOGITS
     closure
    1.45
     closing
    1.38
     opening
    1.36
     reopening
    1.34
     operating
    1.34
     reopen
    1.32
     closures
    1.30
     doors
    1.18
     closed
    1.18
     beroperasi
    1.16
    Activations Density 0.036%

    No Known Activations