© 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. 10-GEMMASCOPE-RES-131K
    7. 8080
    Prev
    Next
    INDEX
    Explanations

    programming, file, code, connection

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags Cyrillic (Russian‐script) tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    꽤
    -2.09
     戰
    -2.06
    嵛
    -1.99
     條
    -1.96
     thankful
    -1.96
     noteworthy
    -1.95
     يول
    -1.95
    ありますが
    -1.88
     to
    -1.85
     einer
    -1.84
    POSITIVE LOGITS
     Chrif
    2.30
     secures
    2.11
    真的很
    2.09
     illuminates
    2.09
     fhould
    2.09
    旰
    2.05
     dieß
    2.02
     scattata
    2.00
     ftate
    1.98
     asserts
    1.98
    Activations Density 0.004%

    No Known Activations