© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1482
    Prev
    Next
    INDEX
    Explanations

    technically

    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
     invece
    -0.83
     particularly
    -0.82
     suspected
    -0.81
    UNIVERS
    -0.80
     badly
    -0.77
    ilions
    -0.76
     alumínio
    -0.75
     profondità
    -0.75
     especially
    -0.74
     vooral
    -0.73
    POSITIVE LOGITS
     technically
    5.78
    Technically
    4.94
     Technically
    4.59
     technical
    4.53
     техни
    4.09
    technical
    4.06
    tech
    4.03
    Technical
    3.80
     Technical
    3.75
     téc
    3.59
    Activations Density 0.155%

    No Known Activations