© 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. 107029
    Prev
    Next
    INDEX
    Explanations

    citations with et al

    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
     jusque
    -1.16
     ferait
    -1.08
     kutoka
    -1.02
    становка
    -0.97
    ופה
    -0.96
     modu
    -0.96
     berechnet
    -0.96
     itinéraires
    -0.94
     firent
    -0.94
     nzuri
    -0.92
    POSITIVE LOGITS
     forthcoming
    3.22
     upcoming
    2.84
     in
    2.84
     submitted
    2.64
     pending
    2.55
    submitted
    2.03
     Submitted
    2.03
    forth
    1.90
    Submitted
    1.89
     awaiting
    1.89
    Activations Density 0.017%

    No Known Activations