© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128417
    Prev
    Next
    INDEX
    Explanations

    words that are/is/to

    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_10/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
     straff
    -1.36
     questi
    -1.29
    
    -1.20
    akteur
    -1.19
     proses
    -1.18
     kompatibel
    -1.16
    ОВО
    -1.16
     Estos
    -1.15
     kuta
    -1.13
     simpel
    -1.13
    POSITIVE LOGITS
     that
    1.45
     purposes
    1.42
     but
    1.37
     always
    1.29
     již
    1.24
     trzeba
    1.23
     “
    1.20
     just
    1.16
     Another
    1.14
     zawsze
    1.14
    Activations Density 0.315%

    No Known Activations