© 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. 10904
    Prev
    Next
    INDEX
    Explanations

    little loves

    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
     goofy
    -1.18
     overal
    -1.01
    Välislingid
    -1.01
    lior
    -0.98
    ESTR
    -0.96
     Achtung
    -0.96
     rick
    -0.96
    basically
    -0.95
    celia
    -0.95
     wacky
    -0.94
    POSITIVE LOGITS
     ;)
    1.36
     sehr
    1.34
     весьма
    1.27
     his
    1.09
     methods
    1.07
     unpleasant
    1.03
     :=
    1.01
     firsthand
    1.01
     😉
    1.00
     with
    0.98
    Activations Density 0.095%

    No Known Activations