© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71178
    Prev
    Next
    INDEX
    Explanations

    past actions and events

    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
     now
    -1.34
     will
    -1.22
     still
    -1.18
     currently
    -1.09
     yet
    -1.08
     one
    -1.05
     presently
    -1.02
    Currently
    -1.02
    现在的
    -0.97
     هنوز
    -0.95
    POSITIVE LOGITS
     was
    1.82
     yesterday
    1.55
     earlier
    1.53
     last
    1.45
     était
    1.34
     שה
    1.31
     было
    1.22
     estava
    1.20
     avait
    1.20
     وكان
    1.17
    Activations Density 0.105%

    No Known Activations