© 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. 50065
    Prev
    Next
    INDEX
    Explanations

    in providing understanding resolving

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

    The neuron appears to be inactive (it does not reliably fire for any specific 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_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
     in
    -1.52
     Zuhause
    -1.23
    には
    -1.22
    もあった
    -1.20
    時間が
    -1.20
     incite
    -1.17
     obligado
    -1.16
    álise
    -1.15
     yapılır
    -1.15
     segíts
    -1.13
    POSITIVE LOGITS
     剧照
    1.53
     the
    1.47
     terms
    1.34
     regards
    1.32
    Jeśli
    1.31
     finding
    1.26
    nemia
    1.25
    袛
    1.24
    eronau
    1.24
    Что
    1.23
    Activations Density 0.089%

    No Known Activations