© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129099
    Prev
    Next
    INDEX
    Explanations

    CSI, scu, CID, TNT, Xinhua

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

    The neuron strongly responds to uppercase acronyms or identifier tokens (e.g. CSI, CID, Xinhua) embedded in the text.

    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
    咴
    -3.13
    猡
    -2.97
    乆
    -2.64
     been
    -2.56
    彞
    -2.53
    幃
    -2.48
    鉿
    -2.42
    ዣ
    -2.42
    肫
    -2.41
    ቍ
    -2.41
    POSITIVE LOGITS
    u
    2.45
    ことはない
    2.44
     builds
    2.38
     unequivocal
    2.38
    籥
    2.36
    昔の
    2.34
     понял
    2.34
    it
    2.31
    翃
    2.25
    ꦫ
    2.22
    Activations Density 0.011%

    No Known Activations