© 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. 103149
    Prev
    Next
    INDEX
    Explanations

    as much

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

    The neuron activates on the comparative phrase “as much.”

    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
    {
    -2.84
    VERY
    -2.47
    쨩
    -2.38
    ᥬ
    -2.28
    ఽ
    -2.27
    }$
    -2.25
    鸶
    -2.20
     vastly
    -2.19
    寕
    -2.17
    狁
    -2.16
    POSITIVE LOGITS
    м
    2.33
    “
    2.31
     than
    2.19
     a
    2.06
     There
    1.98
    just
    1.98
     и
    1.95
     started
    1.95
     from
    1.93
    .”
    1.92
    Activations Density 0.011%

    No Known Activations