© 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. 73898
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
     pittores
    -1.17
     voetballer
    -1.13
     romantis
    -1.10
     Automó
    -1.09
     tetapi
    -1.07
    tritts
    -1.07
     życia
    -1.06
     skå
    -1.05
     mawar
    -1.05
    kapat
    -1.05
    POSITIVE LOGITS
    g
    1.10
     we
    1.07
    h
    1.05
    u
    1.05
    k
    1.03
     Grüßen
    1.00
    also
    0.98
     is
    0.97
    \
    0.96
     who
    0.96
    Activations Density 0.009%

    No Known Activations