© 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. 108106
    Prev
    Next
    INDEX
    Explanations

    people's backgrounds and roles

    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
     Seperti
    -1.26
    ּוֹ
    -1.25
    menü
    -1.16
    Evet
    -1.15
     býval
    -1.12
     rajut
    -1.08
     Może
    -1.08
     Langkah
    -1.04
     Mungkin
    -1.04
     meille
    -1.04
    POSITIVE LOGITS
     disguised
    1.47
     transformed
    1.07
    uzen
    1.03
     promised
    1.02
     concealed
    0.97
     disguise
    0.96
    一天
    0.96
     secretly
    0.95
     magically
    0.93
     trick
    0.92
    Activations Density 0.042%

    No Known Activations