© 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. 99409
    Prev
    Next
    INDEX
    Explanations

    asking for help or instructions

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

    This neuron activates on Russian (Cyrillic‐script) text segments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     kalp
    -1.05
     disiplin
    -1.05
     tiks
    -1.03
     parla
    -1.02
     punya
    -1.02
     lukisan
    -1.00
     diki
    -0.99
     topik
    -0.98
     alamat
    -0.98
     kual
    -0.97
    POSITIVE LOGITS
     hãy
    2.06
     Hãy
    1.71
     yourself
    1.66
     please
    1.63
    Hãy
    1.59
     be
    1.54
     करें
    1.41
     کنید
    1.34
    ведите
    1.29
    ursue
    1.28
    Activations Density 0.060%

    No Known Activations