© 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. 34097
    Prev
    Next
    INDEX
    Explanations

    past time or before now

    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
    犢
    -0.86
     세트
    -0.84
    tedy
    -0.79
     arthur
    -0.79
     louis
    -0.79
     tatsäch
    -0.79
    Iran
    -0.79
    vière
    -0.78
     második
    -0.77
     later
    -0.77
    POSITIVE LOGITS
     previous
    1.53
     years
    1.51
     this
    1.42
     earlier
    1.36
     previously
    1.34
     раньше
    1.27
     selama
    1.23
     before
    1.19
     давно
    1.17
    previously
    1.16
    Activations Density 0.022%

    No Known Activations