© 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. 73766
    Prev
    Next
    INDEX
    Explanations

    Bever, even, if, when

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

    The neuron flags tokens that introduce conditional or concessive clauses (e.g. “if,” “when,” “even if,” Japanese “ても,” “何でも,” etc.).

    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
    ">
    -2.39
     '
    -2.38
    ве
    -2.28
     &
    -2.27
     and
    -2.22
    }.
    -2.14
    ने
    -2.09
     как
    -2.08
    }$.
    -2.08
    end
    -1.98
    POSITIVE LOGITS
    鐿
    2.55
    {
    2.50
    
    2.48
     ersche
    2.45
     feiert
    2.38
     bemer
    2.36
     mogą
    2.36
     môžu
    2.34
     seules
    2.31
     Шаг
    2.27
    Activations Density 0.002%

    No Known Activations