© 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. 102519
    Prev
    Next
    INDEX
    Explanations

    insights into

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

    The neuron activates on occurrences of the word “insights” (or “Insight” in headings).

    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
     This
    -2.91
    1
    -2.48
     These
    -2.47
    2
    -2.41
     powinna
    -2.34
     Why
    -2.33
     Where
    -2.31
     Roughly
    -2.30
     How
    -2.17
     analogous
    -2.13
    POSITIVE LOGITS
    튿
    2.45
    s
    2.42
    ⬯
    2.31
    were
    2.22
    鹉
    2.22
    ޏ
    2.20
     foray
    2.17
    
    2.16
    家が
    2.14
    tempat
    2.11
    Activations Density 0.003%

    No Known Activations