© 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. 28590
    Prev
    Next
    INDEX
    Explanations

    NOUN + SPECIFIC NOUN/CATEGORY

    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
    tront
    -1.11
    lity
    -1.08
    が多く
    -1.06
    fied
    -1.04
     pneumoniae
    -1.03
    mainly
    -1.03
     
    -1.03
    andering
    -1.02
     нашу
    -1.02
     -
    -1.00
    POSITIVE LOGITS
     lavorato
    1.13
     隊
    1.13
     pensato
    1.12
     EVERY
    1.01
     Before
    1.00
     cleverly
    0.96
     найти
    0.95
     pioggia
    0.94
     innovative
    0.93
     potuto
    0.93
    Activations Density 0.080%

    No Known Activations