© 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. 93028
    Prev
    Next
    INDEX
    Explanations

    were followed by verb or adjective

    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
     and
    -2.19
     or
    -2.14
    it
    -2.09
    phere
    -2.05
    沕
    -2.02
    thodoxy
    -1.99
    neling
    -1.95
    your
    -1.90
    zied
    -1.90
     மற்றும்
    -1.88
    POSITIVE LOGITS
     also
    2.73
     able
    2.58
     termed
    2.38
     not
    2.36
     deemed
    2.09
    wolves
    2.03
     regarded
    1.88
     taken
    1.86
     considered
    1.80
     called
    1.80
    Activations Density 0.118%

    No Known Activations