© 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. 95419
    Prev
    Next
    INDEX
    Explanations

    largest or biggest instances

    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
     often
    -1.32
     can
    -1.21
     are
    -1.20
     always
    -1.09
     only
    -1.04
    I
    -1.04
     sometimes
    -1.02
     pouze
    -1.02
    to
    -1.00
    no
    -1.00
    POSITIVE LOGITS
    .'</
    1.19
     unprecedented
    1.17
     gentes
    1.11
     simultaneous
    1.10
     monstruos
    1.09
    トナム
    1.09
     récompenses
    1.09
     filozof
    1.09
     intelek
    1.09
     puntu
    1.08
    Activations Density 0.045%

    No Known Activations