© 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. 54356
    Prev
    Next
    INDEX
    Explanations

    terms followed by specific words

    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
    PRWEB
    -1.11
    karang
    -1.02
     wła
    -1.01
     disant
    -1.00
    cres
    -0.98
     MAKING
    -0.97
     teken
    -0.95
    males
    -0.95
     imprimer
    -0.95
     rowspan
    -0.95
    POSITIVE LOGITS
     because
    1.95
     when
    1.44
     or
    1.27
    because
    1.25
     despite
    1.20
     after
    1.14
     if
    1.12
     çünkü
    1.01
     while
    1.01
    性質
    1.00
    Activations Density 0.036%

    No Known Activations