© 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. 22-GEMMASCOPE-RES-131K
    7. 28603
    Prev
    Next
    INDEX
    Explanations

    Digital Summer

    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
     gyvento
    -1.06
    merkt
    -1.02
     spiegel
    -0.99
    曾经
    -0.98
     dimentic
    -0.97
    "../
    -0.97
     persoane
    -0.96
     metų
    -0.96
     zoude
    -0.95
    tiembre
    -0.93
    POSITIVE LOGITS
     decisiones
    1.19
     our
    1.03
    ñoz
    0.97
    clerview
    0.97
     oświet
    0.93
    8
    0.92
    riotic
    0.91
     lakier
    0.90
     rękaw
    0.90
    捗
    0.90
    Activations Density 0.007%

    No Known Activations