© 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. 22-GEMMASCOPE-RES-131K
    7. 36468
    Prev
    Next
    INDEX
    Explanations

    Is there

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

    This neuron detects words and phrases that introduce or describe the origin, first occurrence, or historical background of a name or family.

    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
     their
    -1.57
     like
    -1.52
     from
    -1.48
     at
    -1.46
     on
    -1.45
     most
    -1.41
     all
    -1.36
    遑
    -1.32
     function
    -1.28
     some
    -1.27
    POSITIVE LOGITS
     araştır
    1.51
    Preparazione
    1.48
    Additionally
    1.44
    Mutability
    1.42
     aprobó
    1.39
     aiuta
    1.35
    りんご
    1.35
     パッド
    1.34
    bbons
    1.34
     ส์
    1.34
    Activations Density 0.001%

    No Known Activations