© 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. 36451
    Prev
    Next
    INDEX
    Explanations

    listing items with counts

    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
    TestingModule
    -1.22
    gms
    -1.13
    xins
    -1.12
    oló
    -1.08
    lossen
    -1.07
    ativní
    -1.07
     تمام
    -1.04
     EditText
    -1.03
     снимка
    -1.02
    uscular
    -1.02
    POSITIVE LOGITS
     a
    1.95
     two
    1.88
     one
    1.56
     several
    1.42
     some
    1.33
     three
    1.27
     five
    1.16
     notícia
    1.12
     twice
    1.12
    が
    1.11
    Activations Density 0.021%

    No Known Activations