© 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. 23889
    Prev
    Next
    INDEX
    Explanations

    matrix rows and columns

    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
     législ
    -0.90
    leč
    -0.75
    🕕
    -0.74
     jopa
    -0.73
     Phoen
    -0.73
    暗
    -0.71
     conquistar
    -0.71
     Recruit
    -0.71
    силання
    -0.71
     Nachteile
    -0.70
    POSITIVE LOGITS
     translation
    1.07
     row
    1.06
     ROW
    1.03
     Row
    1.02
     column
    1.02
    translation
    1.02
     columnas
    0.98
     Translation
    0.98
     COLUMN
    0.97
     rows
    0.96
    Activations Density 0.007%

    No Known Activations