© 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. 22-GEMMASCOPE-RES-131K
    7. 72404
    Prev
    Next
    INDEX
    Explanations

    historical places and entities

    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
     currently
    -2.23
     current
    -1.68
    Currently
    -1.60
    currently
    -1.59
     recently
    -1.59
    目前
    -1.57
     Currently
    -1.46
     presently
    -1.44
     already
    -1.43
     new
    -1.32
    POSITIVE LOGITS
     was
    1.87
     später
    1.50
     era
    1.47
     were
    1.38
    っていた
    1.34
     later
    1.31
     była
    1.27
    后来
    1.26
     would
    1.25
     latach
    1.25
    Activations Density 0.222%

    No Known Activations