© 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. 75073
    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
     their
    -1.35
     or
    -1.33
     it
    -1.32
     receive
    -1.20
     its
    -1.20
     because
    -1.12
     of
    -1.11
    ônico
    -1.09
     created
    -1.09
     having
    -1.08
    POSITIVE LOGITS
    berra
    1.30
    knew
    1.23
     şun
    1.22
     myriad
    1.20
     takich
    1.19
    zzie
    1.18
    chose
    1.18
     revamped
    1.17
     nejen
    1.16
    ebly
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.