© 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. 59204
    Prev
    Next
    INDEX
    Explanations

    job is finished

    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
     accett
    -0.84
     dejes
    -0.79
    otech
    -0.78
    imiento
    -0.77
     iq
    -0.77
    ่อย
    -0.75
     kehilangan
    -0.75
     rimasto
    -0.75
     入れ
    -0.75
    iq
    -0.74
    POSITIVE LOGITS
     finished
    6.16
    finished
    4.78
     Finished
    4.72
    Finished
    4.56
     finish
    4.44
     finishes
    3.80
     done
    3.64
    FINISHED
    3.53
    finish
    3.53
     Finish
    3.28
    Activations Density 0.065%

    No Known Activations