© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98116
    Prev
    Next
    INDEX
    Explanations

    first hour, one voice, million reasons

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

    The neuron strongly fires on rare or unusually infrequent tokens—essentially flagging low-frequency words.

    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
    を
    -1.37
    そして
    -1.22
    特别是
    -1.18
    參考文獻
    -1.17
    特に
    -1.16
    が
    -1.16
     unusually
    -1.16
    。。
    -1.14
    つまり
    -1.13
    信念
    -1.12
    POSITIVE LOGITS
    久し
    1.67
    の方に
    1.63
    さぁ
    1.59
    為に
    1.59
    を探す
    1.52
    すっ
    1.52
    ほうがいい
    1.45
    ビックリ
    1.36
    あぁ
    1.36
    ままで
    1.34
    Activations Density 0.478%

    No Known Activations