© 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. 70199
    Prev
    Next
    INDEX
    Explanations

    music and albums

    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
     supposedly
    -1.16
     apparently
    -1.10
     improve
    -1.06
     reportedly
    -1.02
     allegedly
    -0.99
     improves
    -0.99
     usually
    -0.95
     zwykle
    -0.95
     either
    -0.92
     promotes
    -0.91
    POSITIVE LOGITS
     broderie
    1.08
    feier
    1.06
     triom
    1.05
     noten
    1.03
     bata
    1.03
     digitale
    1.02
     continuer
    1.02
    ervant
    1.02
     Depuis
    1.00
     länder
    1.00
    Activations Density 0.040%

    No Known Activations