© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99251
    Prev
    Next
    INDEX
    Explanations

    second in sequence

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

    This neuron responds to very high‐frequency common English words (e.g. “the,” “a,” “and,” “to,” “that,” 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_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
    Firstly
    -1.01
     endlich
    -1.00
     erstmals
    -0.97
     început
    -0.97
     Firstly
    -0.97
    まずは
    -0.96
    нача
    -0.94
    zugehen
    -0.92
     впервые
    -0.92
    ICALS
    -0.91
    POSITIVE LOGITS
     second
    9.63
    second
    7.00
    第二
    5.84
     zweiten
    5.63
     segunda
    5.63
    Second
    5.56
     segundo
    5.50
    SECOND
    5.25
     zweite
    5.22
     второй
    5.22
    Activations Density 0.318%

    No Known Activations