© 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. 13661
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    brainly
    -1.22
     anche
    -1.20
    PUESTA
    -1.20
     italiens
    -1.16
    ZIONI
    -1.13
    '}';
    -1.09
    pstmt
    -1.09
     Fungsi
    -1.07
     måneder
    -1.06
    ksiyon
    -1.05
    POSITIVE LOGITS
     unwittingly
    1.35
     akin
    1.27
     requesting
    1.17
     instead
    1.16
     conclusively
    1.13
     championed
    1.13
     foremost
    1.12
     powerfully
    1.10
     destined
    1.09
     influencing
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.