© 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. 40734
    Prev
    Next
    INDEX
    Explanations

    IDA, CIS, or IDF acronyms

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

    The neuron fires on occurrences of the three-letter sequence “ida” (e.g. the standalone acronym “IDA” or “.ida” tokens).

    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
    </td>
    -2.47
    ”，
    -2.44
    ”？
    -2.38
    ”、“
    -2.38
    </h5>
    -2.34
    ).
    -2.25
    ”（
    -2.19
     möjligt
    -2.17
    隄
    -2.03
    </h2>
    -2.00
    POSITIVE LOGITS
    </strong>
    2.41
     You
    2.39
    1
    2.19
    訁
    2.09
     \
    2.03
    鸲
    1.98
    感じ
    1.93
     Your
    1.91
     respekt
    1.88
    Ꮉ
    1.88
    Activations Density 0.005%

    No Known Activations