© 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. 67173
    Prev
    Next
    INDEX
    Explanations

    list of items

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

    The neuron detects the standard introductory phrasing of “This is a (partial) list of …” at the start of list‐type articles.

    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
     your
    -1.88
     in
    -1.75
     our
    -1.59
     really
    -1.58
     new
    -1.56
     when
    -1.51
     makes
    -1.45
     during
    -1.45
     first
    -1.44
     creates
    -1.44
    POSITIVE LOGITS
    iress
    1.48
    quirer
    1.48
    킁
    1.40
    significantly
    1.39
    鹩
    1.37
    ׳
    1.36
    provides
    1.35
     fenô
    1.35
    튿
    1.34
    ícias
    1.33
    Activations Density 0.110%

    No Known Activations