© 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. 99714
    Prev
    Next
    INDEX
    Explanations

    "per" followed by specific terms

    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
    timbangan
    -1.09
    ere
    -0.80
     preparare
    -0.80
    m
    -0.78
    hiasan
    -0.78
     likely
    -0.78
     supposed
    -0.76
    i
    -0.75
     otherwise
    -0.75
    erebbe
    -0.74
    POSITIVE LOGITS
     Per
    1.36
     capita
    1.18
     Пер
    1.15
    Per
    1.14
     PER
    1.13
    Percy
    1.02
     Perr
    1.01
    PER
    0.97
     Percy
    0.97
    чування
    0.92
    Activations Density 0.122%

    No Known Activations