© 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. 22-GEMMASCOPE-RES-131K
    7. 34548
    Prev
    Next
    INDEX
    Explanations

    abbreviations in parentheses

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

    The neuron fires on short uppercase abbreviations/acronyms (often in parentheses) such as EPI, ENDO, iP, UMN, DAQ, QbD, ERT, IEF, IETF, ETT, or ACD.

    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
    Of
    -2.69
    The
    -2.67
    What
    -2.61
    When
    -2.56
    If
    -2.56
    Because
    -2.55
    Just
    -2.53
    After
    -2.52
    Despite
    -2.50
     illustrious
    -2.48
    POSITIVE LOGITS
     "*
    2.36
     テープ
    2.17
     ModelExpression
    1.91
     dalších
    1.91
     dritte
    1.91
     jiné
    1.88
     سایر
    1.88
    缯
    1.87
    癭
    1.86
    和她
    1.84
    Activations Density 0.135%

    No Known Activations