© 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. 22-GEMMASCOPE-RES-131K
    7. 14172
    Prev
    Next
    INDEX
    Explanations

    prefixes like Pol:, Cong:, Founded:

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

    The neuron fires on non-English (particularly Portuguese) words and phrases, effectively spotting foreign-language 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_22/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
     både
    -1.02
    說道
    -0.97
    ++.
    -0.97
     みた
    -0.94
     botones
    -0.93
     skru
    -0.92
    ?».
    -0.91
     bébé
    -0.91
     ferien
    -0.91
     ekos
    -0.91
    POSITIVE LOGITS
    urlencoded
    0.96
    rendon
    0.94
    ″]
    0.94
    Törté
    0.93
    ائل
    0.93
    parsedMessage
    0.93
    fiore
    0.92
    CPT
    0.92
    Clasificación
    0.92
    هاب
    0.91
    Activations Density 0.002%

    No Known Activations