© 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. 12811
    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
     until
    -1.24
     or
    -1.16
     all
    -1.16
     their
    -1.09
     those
    -1.02
     both
    -1.02
     Then
    -0.98
     only
    -0.94
     they
    -0.93
     just
    -0.93
    POSITIVE LOGITS
     maniere
    1.28
     multicolore
    1.19
    ᴋ
    1.15
     téléph
    1.12
     penser
    1.09
     déchir
    1.08
     alho
    1.08
    我們的
    1.07
    flasche
    1.07
     navidad
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.