© 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. 38295
    Prev
    Next
    INDEX
    Explanations

    time indicators

    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
     kasama
    -1.25
    лександр
    -1.08
     supposedly
    -1.05
     ngayon
    -1.05
     ngunit
    -1.04
     it
    -1.01
     ostensibly
    -1.00
     conex
    -0.98
     Tarif
    -0.96
     jika
    -0.96
    POSITIVE LOGITS
     at
    1.97
     meistens
    1.11
     einzeln
    1.09
     auswählen
    1.06
     nabíz
    1.04
     öfter
    1.02
     lúc
    1.02
    トリック
    1.01
     fervent
    1.01
     noon
    1.00
    Activations Density 0.007%

    No Known Activations