© 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. 76750
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     burgeoning
    -1.19
     Though
    -1.13
     could
    -1.12
     perpetually
    -1.06
     presently
    -1.01
     strangely
    -1.01
     extraordinarily
    -1.00
     considerably
    -0.99
     oddly
    -0.99
     having
    -0.98
    POSITIVE LOGITS
     https
    1.19
    sometimes
    1.11
     seksi
    1.10
     souvent
    1.08
     lagar
    1.07
     triko
    1.05
     kaki
    1.04
     Meksi
    1.04
     geene
    1.02
     parfois
    1.00
    Activations Density 0.001%

    No Known Activations