© 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. 34-GEMMASCOPE-RES-131K
    7. 33841
    Prev
    Next
    INDEX
    Explanations

    solidity contract code

    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_34/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
     Elden
    -0.86
    チコミ
    -0.75
    很快就
    -0.73
    tikel
    -0.71
     län
    -0.71
    canton
    -0.71
    🅃
    -0.70
    Horace
    -0.69
     téléchargement
    -0.68
     enquired
    -0.68
    POSITIVE LOGITS
    Ow
    1.23
     Ow
    1.16
     onlyOwner
    1.02
     mortal
    0.94
    Modifiers
    0.94
     owner
    0.90
    owner
    0.90
     SafeMath
    0.84
     saf
    0.84
    onade
    0.82
    Activations Density 0.031%

    No Known Activations