© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47291
    Prev
    Next
    INDEX
    Explanations

    set/get/remove operations

    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
    Negative Logits
    dexter
    -0.84
     boste
    -0.82
    getItemId
    -0.81
     témoignages
    -0.77
    HSA
    -0.77
    颔
    -0.76
    Hons
    -0.75
    setattr
    -0.75
     compétences
    -0.75
    ہ
    -0.74
    POSITIVE LOGITS
     unset
    1.07
    获取
    1.00
    unset
    0.94
     get
    0.93
     existing
    0.89
     gotten
    0.84
     retrieve
    0.84
     gets
    0.83
    AndGet
    0.81
     것을
    0.81
    Activations Density 0.009%

    No Known Activations