© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33273
    Prev
    Next
    INDEX
    Explanations

    code and data types

    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
     célè
    -1.61
    鳚
    -1.54
     téléph
    -1.54
     dépens
    -1.52
     mariposa
    -1.52
     éta
    -1.51
     balení
    -1.48
     pérd
    -1.48
     refroid
    -1.45
     élas
    -1.45
    POSITIVE LOGITS
     J
    1.46
     S
    1.45
     all
    1.44
     these
    1.38
     to
    1.37
     L
    1.37
     C
    1.36
     D
    1.35
    z
    1.32
     M
    1.31
    Activations Density 0.043%

    No Known Activations