© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39396
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

    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
     alfombra
    -1.09
    essentiel
    -1.07
    豇
    -1.03
    napp
    -1.02
     aplicaciones
    -1.02
     juiste
    -1.01
     větší
    -1.01
    -<
    -1.00
    atherine
    -0.99
     mercancías
    -0.98
    POSITIVE LOGITS
     which
    1.46
     one
    1.34
     of
    1.21
     where
    1.16
     through
    1.02
     having
    1.00
     called
    0.98
     From
    0.96
     at
    0.94
     on
    0.94
    Activations Density 0.086%

    No Known Activations