© 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. 10-GEMMASCOPE-RES-131K
    7. 130082
    Prev
    Next
    INDEX
    Explanations

    something or things followed by detail

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

    The neuron fires strongly on vague placeholders and catch-all referent words like “something,” “anything,” and “things.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Ꮼ
    -1.52
     We
    -1.42
    Zubereitung
    -1.39
    ㅌ
    -1.38
    ࿚
    -1.37
     entirety
    -1.34
    tinggi
    -1.34
    président
    -1.34
    drei
    -1.32
    Folge
    -1.32
    POSITIVE LOGITS
     about
    2.11
     that
    1.91
     although
    1.73
     they
    1.73
     regarding
    1.71
     with
    1.59
    For
    1.57
    although
    1.56
     how
    1.54
     despite
    1.52
    Activations Density 0.053%

    No Known Activations