© 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. 160
    Prev
    Next
    INDEX
    Explanations

    hollow_list

    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
     could
    -1.37
     that
    -1.30
     those
    -1.23
     might
    -1.20
     publicado
    -1.19
     without
    -1.16
     became
    -1.16
     will
    -1.15
     may
    -1.14
     these
    -1.13
    POSITIVE LOGITS
     Dinas
    1.21
     compromis
    1.16
     différents
    1.11
     râ
    1.06
     quitt
    1.05
     participer
    1.03
     assister
    1.03
     chers
    1.02
     misst
    1.02
    managed
    1.01
    Activations Density 0.010%

    No Known Activations