© 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. 34-GEMMASCOPE-RES-131K
    7. 81592
    Prev
    Next
    INDEX
    Explanations

    notable people

    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_34/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
    Dzięki
    -1.09
     Nedir
    -1.09
     tenisky
    -1.06
     säkert
    -1.05
     ändå
    -1.02
     äldre
    -1.02
     olika
    -1.02
     alimentos
    -1.02
    policies
    -1.00
    Evet
    -1.00
    POSITIVE LOGITS
    if
    1.70
     if
    1.34
     instead
    1.14
     rather
    1.13
     these
    1.06
    s
    1.02
     Meanwhile
    1.00
     yet
    0.96
     we
    0.95
     a
    0.95
    Activations Density 0.001%

    No Known Activations