© 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. 112919
    Prev
    Next
    INDEX
    Explanations

    various endings or structures

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

    The neuron strongly activates on words appearing in document titles, headings, or section titles.

    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
    ="
    -1.69
     then
    -1.56
     zawsze
    -1.51
    9
    -1.49
     Then
    -1.49
    3
    -1.40
     для
    -1.36
    arme
    -1.34
    5
    -1.31
    ђа
    -1.29
    POSITIVE LOGITS
     its
    2.17
    diğinde
    1.32
     它
    1.32
     who
    1.31
    mmons
    1.25
     aceea
    1.20
    ることができます
    1.20
     does
    1.20
     salita
    1.18
    的基础
    1.17
    Activations Density 0.167%

    No Known Activations