© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90598
    Prev
    Next
    INDEX
    Explanations

    achieved success or distinction

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

    the neuron activates on mentions of someone “achieving” a specific quantified result or milestone (i.e. “achieved” followed by a number).

    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
     of
    -2.25
     you
    -1.89
     fijne
    -1.69
     then
    -1.66
     [];
    -1.60
    BURGH
    -1.59
     gezond
    -1.58
     éves
    -1.57
    /",
    -1.51
     instead
    -1.49
    POSITIVE LOGITS
     PRIOR
    1.80
    Анна
    1.55
    Before
    1.54
    1.44
     dominance
    1.41
    Mitä
    1.41
    Perhaps
    1.40
    Despite
    1.38
    n
    1.38
     a
    1.34
    Activations Density 0.032%

    No Known Activations