© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71980
    Prev
    Next
    INDEX
    Explanations

    punk rock bands

    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_22/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
     jūs
    -1.08
     results
    -1.08
     beneficial
    -1.07
    ?
    -1.07
     benefits
    -1.06
    e
    -1.06
      
    -1.05
     tasks
    -1.00
    i
    -0.99
    u
    -0.98
    POSITIVE LOGITS
     punk
    1.45
    zości
    1.41
    elung
    1.35
    пуль
    1.25
     ),
    1.21
    iconductors
    1.20
    izielle
    1.20
    POSURE
    1.19
    faktor
    1.17
    LowerCase
    1.16
    Activations Density 0.062%

    No Known Activations