© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11029
    Prev
    Next
    INDEX
    Explanations

    best of the best

    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
     with
    -1.09
    largest
    -1.02
     =
    -0.98
    ent
    -0.96
    ini
    -0.96
    :
    -0.95
    is
    -0.93
     beverly
    -0.91
    navigationItem
    -0.91
     largest
    -0.91
    POSITIVE LOGITS
     intelek
    1.22
     récomp
    1.22
     harten
    1.13
     sija
    1.13
     trinken
    1.13
     religieuses
    1.12
     spus
    1.10
     nimmer
    1.10
     pimenta
    1.07
     écl
    1.07
    Activations Density 0.033%

    No Known Activations