© 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. 93221
    Prev
    Next
    INDEX
    Explanations

    has been since

    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
     still
    -2.39
     will
    -1.30
     first
    -1.29
     now
    -1.27
     knew
    -1.16
    まだまだ
    -1.16
     did
    -1.15
     would
    -1.13
     might
    -1.13
     gave
    -1.08
    POSITIVE LOGITS
     since
    3.17
    since
    2.41
     SINCE
    2.34
     lately
    2.27
     depuis
    2.19
     منذ
    2.16
     sejak
    2.06
     been
    1.84
     bisher
    1.71
     desde
    1.70
    Activations Density 0.117%

    No Known Activations