© 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. 36384
    Prev
    Next
    INDEX
    Explanations

    subsequent 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
    Hanya
    -1.13
     حتی
    -1.06
    
    -1.03
     ceux
    -1.01
    ticularly
    -0.98
     auraient
    -0.97
     forcément
    -0.97
     renon
    -0.97
     kaum
    -0.96
    なんて
    -0.95
    POSITIVE LOGITS
     later
    4.28
     nantinya
    2.86
     später
    2.73
    later
    2.66
     Later
    2.59
    Later
    2.34
     senere
    2.34
     will
    2.25
     subsequently
    2.23
     posteriormente
    2.16
    Activations Density 0.040%

    No Known Activations