© 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. 34-GEMMASCOPE-RES-131K
    7. 30616
    Prev
    Next
    INDEX
    Explanations

    place name prefixes and suffixes

    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
    でしょうね
    -1.20
    動機
    -1.19
    強烈
    -1.11
     cæ
    -1.08
    🫓
    -1.06
    母親
    -1.05
    <bos>
    -1.00
    📉
    -0.99
     campesinos
    -0.98
    akterysty
    -0.97
    POSITIVE LOGITS
     игро
    1.05
    際は
    1.05
    も行
    1.04
    必要がある
    1.02
    たびに
    1.01
    +```
    0.97
     EconPapers
    0.96
     Además
    0.95
    の方に
    0.94
    ״
    0.94
    Activations Density 0.179%

    No Known Activations