© 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. 10-GEMMASCOPE-RES-131K
    7. 47672
    Prev
    Next
    INDEX
    Explanations

    so-called terms

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

    The neuron activates on phrases that introduce or label something by name—e.g. “called,” “so‐called,” or “what’s called” constructions.

    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
    dáms
    -1.60
    Ꮸ
    -1.60
    どちら
    -1.52
    Hilsen
    -1.49
    あなたの
    -1.49
    ñada
    -1.44
     alkoholu
    -1.44
    這個
    -1.42
    
    -1.41
     doká
    -1.41
    POSITIVE LOGITS
     '
    1.86
     called
    1.66
     “
    1.59
     we
    1.51
    .”
    1.49
     by
    1.48
    section
    1.39
     a
    1.38
     tzw
    1.35
    called
    1.34
    Activations Density 0.025%

    No Known Activations