© 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. 7118
    Prev
    Next
    INDEX
    Explanations

    on the part of

    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
     Pfar
    -0.79
     XXVII
    -0.74
     Tief
    -0.73
    たたみ
    -0.73
     Sections
    -0.72
     Sect
    -0.71
    ้ว
    -0.70
     Dal
    -0.68
    ↑
    -0.68
    prin
    -0.67
    POSITIVE LOGITS
     part
    4.03
    part
    2.73
     behalf
    2.42
     parte
    2.42
    Part
    2.23
     side
    2.14
     سوی
    2.09
     phía
    1.96
     стороны
    1.95
    seits
    1.95
    Activations Density 0.017%

    No Known Activations