© 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. 22-GEMMASCOPE-RES-131K
    7. 66685
    Prev
    Next
    INDEX
    Explanations

    sports and references

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

    The neuron is strongly activated by tokens from external link or reference URLs (e.g. domain names and site names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     you
    -1.59
     your
    -1.44
     
    -1.40
     a
    -1.21
    ,”
    -1.19
     an
    -1.18
     Técnicas
    -1.17
     should
    -1.13
     Méndez
    -1.13
     Sistemas
    -1.10
    POSITIVE LOGITS
    معرفی
    1.44
    Materiál
    1.40
     conosce
    1.36
    توضیحات
    1.34
     parteci
    1.31
     recherchez
    1.29
     JOSÉ
    1.28
    Leírás
    1.23
     作り方
    1.23
     crescere
    1.23
    Activations Density 0.016%

    No Known Activations