© 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. 112145
    Prev
    Next
    INDEX
    Explanations

    than, of, as comparatives

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

    The neuron fires on descriptive adjective tokens (i.e. quality-describing words).

    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
    ?
    -1.82
     by
    -1.68
     ''
    -1.58
     to
    -1.52
     The
    -1.50
     who
    -1.46
     beijo
    -1.46
    ).
    -1.44
     veja
    -1.43
     esboço
    -1.40
    POSITIVE LOGITS
     тебя
    1.43
    horabuena
    1.43
     imperative
    1.43
     вас
    1.37
     Traducción
    1.35
    kita
    1.33
    套路
    1.32
     musisz
    1.31
    よいよ
    1.31
     możesz
    1.31
    Activations Density 0.076%

    No Known Activations