© 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. 10-GEMMASCOPE-RES-131K
    7. 8835
    Prev
    Next
    INDEX
    Explanations

    ISO-8859-1 charset

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

    The neuron strongly activates on Cyrillic‐script sequences (i.e. Russian/Ukrainian 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_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
    」　
    -2.58
    </i>
    -2.56
    </h1>
    -2.53
    齶
    -2.33
     It
    -2.27
    鹟
    -2.25
    甃
    -2.23
    )」
    -2.20
     沈
    -2.19
    <i>
    -2.17
    POSITIVE LOGITS
    ]
    2.70
    </em>
    2.70
    をしていた
    2.45
    man
    2.23
    </h4>
    2.17
    
    2.13
    <bos>
    2.09
    tamaris
    2.06
    式的
    2.03
    当时的
    2.03
    Activations Density 0.006%

    No Known Activations