© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7938
    Prev
    Next
    INDEX
    Explanations

    preparation

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

    The neuron strongly activates on words and word stems referring to preparation or getting ready (e.g. “preparation,” “prepare,” “preparing”).

    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
    \\
    -1.70
    ).
    -1.70
    $,
    -1.63
    )$,
    -1.58
     первые
    -1.57
    }$,
    -1.50
    '
    -1.49
    汌
    -1.48
     putative
    -1.48
     kooper
    -1.45
    POSITIVE LOGITS
    preparation
    1.63
     However
    1.56
    requent
    1.55
    Hermoso
    1.51
    慥
    1.50
     Prepare
    1.50
     According
    1.48
    そうで
    1.45
     Preparation
    1.42
    vanju
    1.42
    Activations Density 0.036%

    No Known Activations