© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16079
    Prev
    Next
    INDEX
    Explanations

    to indicates destination

    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
     incluso
    -1.27
     même
    -1.06
    两次
    -1.02
    会导致
    -0.94
     حتی
    -0.94
     sommige
    -0.92
     nawet
    -0.90
    vfill
    -0.90
     даже
    -0.90
    ↵
    -0.89
    POSITIVE LOGITS
     another
    1.62
     further
    1.55
     to
    1.52
     weiteren
    1.25
     elsewhere
    1.22
    toMap
    1.14
     berikutnya
    1.09
    graphers
    1.09
     ulteriori
    1.09
     selanjutnya
    1.05
    Activations Density 0.033%

    No Known Activations