© 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. 54240
    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
    It
    -1.19
    4
    -1.07
     térmico
    -1.07
     ExecuteAsync
    -1.05
     both
    -1.03
     zusätzlichen
    -1.03
     technischen
    -1.02
    了自己
    -1.01
     the
    -0.99
    終わった
    -0.98
    POSITIVE LOGITS
     InputMaybe
    1.23
     sánh
    1.19
     februar
    1.19
     incroy
    1.18
    [:,:,
    1.14
     attribué
    1.13
     kjem
    1.13
     magnifiques
    1.13
    bigr
    1.13
    astă
    1.13
    Activations Density 0.000%

    No Known Activations