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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12272
    Prev
    Next
    INDEX
    Explanations

    equation numbers or references

    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
     so
    -1.10
    🐕
    -1.05
    $
    -0.97
     botas
    -0.97
     Ž
    -0.97
    ()]
    -0.94
    ⛳
    -0.94
    лару
    -0.94
     persones
    -0.94
     marco
    -0.93
    POSITIVE LOGITS
    不仅仅
    1.07
    きち
    0.99
     edifici
    0.98
    でん
    0.96
     namentlich
    0.95
     sumptuous
    0.94
     Deinen
    0.93
     brilhante
    0.92
     pursued
    0.89
    ardige
    0.89
    Activations Density 0.005%

    No Known Activations