© 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. 85735
    Prev
    Next
    INDEX
    Explanations

    Evaluations and specifications

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

    The neuron fires on quantifier-based comparison phrases (e.g. “nothing short of,” “no less than,” “fewer than,” “less than”).

    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
    呟
    -1.81
    Տես
    -1.70
    nicht
    -1.70
    weitere
    -1.65
    揶
    -1.62
     tantangan
    -1.61
     začet
    -1.55
     keinginan
    -1.51
    咂
    -1.50
    总经理
    -1.49
    POSITIVE LOGITS
    ).
    1.71
    ".
    1.59
     have
    1.58
    1
    1.56
    =
    1.49
     becau
    1.44
     explained
    1.43
    We
    1.43
     beca
    1.43
     de
    1.42
    Activations Density 0.004%

    No Known Activations