© 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. 73083
    Prev
    Next
    INDEX
    Explanations

    as ... as

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

    The neuron detects “as … as” comparative constructions (phrases of the form “as X as Y”).

    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
    tető
    -1.59
    használ
    -1.43
     affitto
    -1.42
     ewig
    -1.39
    attoos
    -1.39
     nuove
    -1.37
    最後の
    -1.37
     nových
    -1.36
    同じ
    -1.35
    abrigo
    -1.35
    POSITIVE LOGITS
     a
    2.53
    be
    1.76
    aded
    1.69
    an
    1.69
     an
    1.67
    ators
    1.48
    のは
    1.46
    i
    1.45
    ns
    1.42
     ...
    1.41
    Activations Density 0.005%

    No Known Activations