© 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. 60722
    Prev
    Next
    INDEX
    Explanations

    previous and next

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

    This neuron detects occurrences of the word “previous” (including variants like “previousElement” or “previous initialization”).

    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
    その後
    -0.86
    ьев
    -0.81
    ě
    -0.78
    Parliament
    -0.78
    ฤษ
    -0.77
    mography
    -0.77
    ﻮ
    -0.77
     puder
    -0.76
     待
    -0.75
     taked
    -0.75
    POSITIVE LOGITS
     now
    0.86
     brick
    0.73
    異
    0.71
     rękaw
    0.71
     augen
    0.70
     MIGHT
    0.70
     अब
    0.69
     Zauber
    0.69
    ᠮ
    0.68
    fart
    0.68
    Activations Density 0.033%

    No Known Activations