© 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. 48920
    Prev
    Next
    INDEX
    Explanations

    Persian and Iranian names and places

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

    The neuron fires strongly on Persian‐language text (i.e. sequences of Persian script characters).

    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
     which
    -1.16
     ہیں
    -1.14
    بیش
    -1.07
     کرنے
    -1.06
     لئے
    -1.02
    šiu
    -1.01
    سرائ
    -0.98
     srebr
    -0.96
     forteller
    -0.94
    توضی
    -0.93
    POSITIVE LOGITS
     люб
    1.13
     sadness
    1.12
     ân
    1.09
     delectable
    1.09
     bleak
    1.09
     brazen
    1.09
    retten
    1.06
     ridiculous
    1.06
     Katal
    1.05
     glede
    1.05
    Activations Density 0.001%

    No Known Activations