© 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. 35728
    Prev
    Next
    INDEX
    Explanations

    simple, clean, sturdy, reliable, easy

    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
    lihood
    -1.55
    opies
    -1.55
    hoppers
    -1.55
    tiy
    -1.55
     pérd
    -1.54
    ebly
    -1.53
    mability
    -1.51
    carus
    -1.48
    itisation
    -1.48
    vermectin
    -1.48
    POSITIVE LOGITS
     and
    2.19
     but
    1.38
     easy
    1.34
     n
    1.32
     has
    1.30
     especially
    1.26
     c
    1.22
     got
    1.20
     constantly
    1.17
     b
    1.16
    Activations Density 0.031%

    No Known Activations