© 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. 67819
    Prev
    Next
    INDEX
    Explanations

    news outlet reporting

    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
    -1.34
     you
    -1.20
     Probably
    -1.17
     probably
    -1.01
     all
    -0.99
    Probably
    -0.98
    !
    -0.97
    ;
    -0.96
     There
    -0.96
     one
    -0.96
    POSITIVE LOGITS
    previously
    1.26
     yesterday
    1.26
     earlier
    1.23
     étui
    1.20
    earlier
    1.17
    もあって
    1.17
    があるので
    1.13
    issé
    1.13
     twarzy
    1.12
    rée
    1.11
    Activations Density 0.018%

    No Known Activations