© 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. 14580
    Prev
    Next
    INDEX
    Explanations

    various languages and scripts

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

    The neuron detects comparative or emphatic discourse markers—words like “basically,” “compared,” “than,” “enough,” and similar intensifiers used in comparisons.

    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
     these
    -1.47
     superbly
    -1.46
     citado
    -1.45
     after
    -1.41
    🩱
    -1.40
    Pře
    -1.39
     गर्न
    -1.39
     शुर
    -1.38
    vlád
    -1.38
    #
    -1.36
    POSITIVE LOGITS
    ଵ
    1.51
     плохо
    1.49
     добавить
    1.40
     créer
    1.38
     evenement
    1.35
    毟
    1.35
     indisponible
    1.32
     простой
    1.31
    gema
    1.31
    Their
    1.31
    Activations Density 0.099%

    No Known Activations